diff options
| author | Shay <hillerys@element.io> | 2022-08-24 14:18:31 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2022-08-24 14:18:31 -0700 |
| commit | 172b651832cea2d832beb5c4ff5bfae4581c8e63 (patch) | |
| tree | ebd49a80d21b84b51606da49d2a94241d4f1c13a | |
| parent | fix test to align with new behaviour (diff) | |
| parent | Rename `event_map` to `unpersisted_events` (#13603) (diff) | |
| download | synapse-172b651832cea2d832beb5c4ff5bfae4581c8e63.tar.xz | |
Merge branch 'develop' into shay/batch_events
155 files changed, 6696 insertions, 3761 deletions
diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml index 4bc29c8207..144cb9ffaa 100644 --- a/.github/workflows/tests.yml +++ b/.github/workflows/tests.yml @@ -53,10 +53,22 @@ jobs: env: PULL_REQUEST_NUMBER: ${{ github.event.number }} + lint-pydantic: + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v2 + with: + ref: ${{ github.event.pull_request.head.sha }} + fetch-depth: 0 + - uses: matrix-org/setup-python-poetry@v1 + with: + extras: "all" + - run: poetry run scripts-dev/check_pydantic_models.py + # Dummy step to gate other tests on without repeating the whole list linting-done: if: ${{ !cancelled() }} # Run this even if prior jobs were skipped - needs: [lint, lint-crlf, lint-newsfile, check-sampleconfig, check-schema-delta] + needs: [lint, lint-crlf, lint-newsfile, lint-pydantic, check-sampleconfig, check-schema-delta] runs-on: ubuntu-latest steps: - run: "true" diff --git a/.github/workflows/triage-incoming.yml b/.github/workflows/triage-incoming.yml new file mode 100644 index 0000000000..8467970128 --- /dev/null +++ b/.github/workflows/triage-incoming.yml @@ -0,0 +1,28 @@ +name: Move new issues into the issue triage board + +on: + issues: + types: [ opened ] + +jobs: + add_new_issues: + name: Add new issues to the triage board + runs-on: ubuntu-latest + steps: + - uses: octokit/graphql-action@v2.x + id: add_to_project + with: + headers: '{"GraphQL-Features": "projects_next_graphql"}' + query: | + mutation add_to_project($projectid:ID!,$contentid:ID!) { + addProjectNextItem(input:{projectId:$projectid contentId:$contentid}) { + projectNextItem { + id + } + } + } + projectid: ${{ env.PROJECT_ID }} + contentid: ${{ github.event.issue.node_id }} + env: + PROJECT_ID: "PVT_kwDOAIB0Bs4AFDdZ" + GITHUB_TOKEN: ${{ secrets.ELEMENT_BOT_TOKEN }} diff --git a/.github/workflows/triage_labelled.yml b/.github/workflows/triage_labelled.yml new file mode 100644 index 0000000000..fbd55de17f --- /dev/null +++ b/.github/workflows/triage_labelled.yml @@ -0,0 +1,44 @@ +name: Move labelled issues to correct projects + +on: + issues: + types: [ labeled ] + +jobs: + move_needs_info: + name: Move X-Needs-Info on the triage board + runs-on: ubuntu-latest + if: > + contains(github.event.issue.labels.*.name, 'X-Needs-Info') + steps: + - uses: octokit/graphql-action@v2.x + id: add_to_project + with: + headers: '{"GraphQL-Features": "projects_next_graphql"}' + query: | + mutation { + updateProjectV2ItemFieldValue( + input: { + projectId: $projectid + itemId: $contentid + fieldId: $fieldid + value: { + singleSelectOptionId: "Todo" + } + } + ) { + projectV2Item { + id + } + } + } + + projectid: ${{ env.PROJECT_ID }} + contentid: ${{ github.event.issue.node_id }} + fieldid: ${{ env.FIELD_ID }} + optionid: ${{ env.OPTION_ID }} + env: + PROJECT_ID: "PVT_kwDOAIB0Bs4AFDdZ" + GITHUB_TOKEN: ${{ secrets.ELEMENT_BOT_TOKEN }} + FIELD_ID: "PVTSSF_lADOAIB0Bs4AFDdZzgC6ZA4" + OPTION_ID: "ba22e43c" diff --git a/CHANGES.md b/CHANGES.md index 0bc8f95855..14fafc260d 100644 --- a/CHANGES.md +++ b/CHANGES.md @@ -1,3 +1,90 @@ +Synapse 1.66.0rc1 (2022-08-23) +============================== + +This release removes the ability for homeservers to delegate email ownership +verification and password reset confirmation to identity servers. This removal +was originally planned for Synapse 1.64, but was later deferred until now. + +See the [upgrade notes](https://matrix-org.github.io/synapse/v1.66/upgrade.html#upgrading-to-v1660) for more details. + +Features +-------- + +- Improve validation of request bodies for the following client-server API endpoints: [`/account/password`](https://spec.matrix.org/v1.3/client-server-api/#post_matrixclientv3accountpassword), [`/account/password/email/requestToken`](https://spec.matrix.org/v1.3/client-server-api/#post_matrixclientv3accountpasswordemailrequesttoken), [`/account/deactivate`](https://spec.matrix.org/v1.3/client-server-api/#post_matrixclientv3accountdeactivate) and [`/account/3pid/email/requestToken`](https://spec.matrix.org/v1.3/client-server-api/#post_matrixclientv3account3pidemailrequesttoken). ([\#13188](https://github.com/matrix-org/synapse/issues/13188), [\#13563](https://github.com/matrix-org/synapse/issues/13563)) +- Add forgotten status to [Room Details Admin API](https://matrix-org.github.io/synapse/latest/admin_api/rooms.html#room-details-api). ([\#13503](https://github.com/matrix-org/synapse/issues/13503)) +- Add an experimental implementation for [MSC3852 (Expose user agents on `Device`)](https://github.com/matrix-org/matrix-spec-proposals/pull/3852). ([\#13549](https://github.com/matrix-org/synapse/issues/13549)) +- Add `org.matrix.msc2716v4` experimental room version with updated content fields. Part of [MSC2716 (Importing history)](https://github.com/matrix-org/matrix-spec-proposals/pull/2716). ([\#13551](https://github.com/matrix-org/synapse/issues/13551)) +- Add support for compression to federation responses. ([\#13537](https://github.com/matrix-org/synapse/issues/13537)) +- Improve performance of sending messages in rooms with thousands of local users. ([\#13522](https://github.com/matrix-org/synapse/issues/13522), [\#13547](https://github.com/matrix-org/synapse/issues/13547)) + + +Bugfixes +-------- + +- Faster room joins: make `/joined_members` block whilst the room is partial stated. ([\#13514](https://github.com/matrix-org/synapse/issues/13514)) +- Fix a bug introduced in Synapse 1.21.0 where the [`/event_reports` Admin API](https://matrix-org.github.io/synapse/develop/admin_api/event_reports.html) could return a total count which was larger than the number of results you can actually query for. ([\#13525](https://github.com/matrix-org/synapse/issues/13525)) +- Fix a bug introduced in Synapse 1.52.0 where sending server notices fails if `max_avatar_size` or `allowed_avatar_mimetypes` is set and not `system_mxid_avatar_url`. ([\#13566](https://github.com/matrix-org/synapse/issues/13566)) +- Fix a bug where the `opentracing.force_tracing_for_users` config option would not apply to [`/sendToDevice`](https://spec.matrix.org/v1.3/client-server-api/#put_matrixclientv3sendtodeviceeventtypetxnid) and [`/keys/upload`](https://spec.matrix.org/v1.3/client-server-api/#post_matrixclientv3keysupload) requests. ([\#13574](https://github.com/matrix-org/synapse/issues/13574)) + + +Improved Documentation +---------------------- + +- Add `openssl` example for generating registration HMAC digest. ([\#13472](https://github.com/matrix-org/synapse/issues/13472)) +- Tidy up Synapse's README. ([\#13491](https://github.com/matrix-org/synapse/issues/13491)) +- Document that event purging related to the `redaction_retention_period` config option is executed only every 5 minutes. ([\#13492](https://github.com/matrix-org/synapse/issues/13492)) +- Add a warning to retention documentation regarding the possibility of database corruption. ([\#13497](https://github.com/matrix-org/synapse/issues/13497)) +- Document that the `DOCKER_BUILDKIT=1` flag is needed to build the docker image. ([\#13515](https://github.com/matrix-org/synapse/issues/13515)) +- Add missing links in `user_consent` section of configuration manual. ([\#13536](https://github.com/matrix-org/synapse/issues/13536)) +- Fix the doc and some warnings that were referring to the nonexistent `custom_templates_directory` setting (instead of `custom_template_directory`). ([\#13538](https://github.com/matrix-org/synapse/issues/13538)) + + +Deprecations and Removals +------------------------- + +- Remove the ability for homeservers to delegate email ownership verification + and password reset confirmation to identity servers. See [upgrade notes](https://matrix-org.github.io/synapse/v1.66/upgrade.html#upgrading-to-v1660) for more details. + +Internal Changes +---------------- + +### Faster room joins + +- Update the rejected state of events during de-partial-stating. ([\#13459](https://github.com/matrix-org/synapse/issues/13459)) +- Avoid blocking lazy-loading `/sync`s during partial joins due to remote memberships. Pull remote memberships from auth events instead of the room state. ([\#13477](https://github.com/matrix-org/synapse/issues/13477)) +- Refuse to start when faster joins is enabled on a deployment with workers, since worker configurations are not currently supported. ([\#13531](https://github.com/matrix-org/synapse/issues/13531)) + +### Metrics and tracing + +- Allow use of both `@trace` and `@tag_args` stacked on the same function. ([\#13453](https://github.com/matrix-org/synapse/issues/13453)) +- Instrument the federation/backfill part of `/messages` for understandable traces in Jaeger. ([\#13489](https://github.com/matrix-org/synapse/issues/13489)) +- Instrument `FederationStateIdsServlet` (`/state_ids`) for understandable traces in Jaeger. ([\#13499](https://github.com/matrix-org/synapse/issues/13499), [\#13554](https://github.com/matrix-org/synapse/issues/13554)) +- Track HTTP response times over 10 seconds from `/messages` (`synapse_room_message_list_rest_servlet_response_time_seconds`). ([\#13533](https://github.com/matrix-org/synapse/issues/13533)) +- Add metrics to track how the rate limiter is affecting requests (sleep/reject). ([\#13534](https://github.com/matrix-org/synapse/issues/13534), [\#13541](https://github.com/matrix-org/synapse/issues/13541)) +- Add metrics to time how long it takes us to do backfill processing (`synapse_federation_backfill_processing_before_time_seconds`, `synapse_federation_backfill_processing_after_time_seconds`). ([\#13535](https://github.com/matrix-org/synapse/issues/13535), [\#13584](https://github.com/matrix-org/synapse/issues/13584)) +- Add metrics to track rate limiter queue timing (`synapse_rate_limit_queue_wait_time_seconds`). ([\#13544](https://github.com/matrix-org/synapse/issues/13544)) +- Update metrics to track `/messages` response time by room size. ([\#13545](https://github.com/matrix-org/synapse/issues/13545)) + +### Everything else + +- Refactor methods in `synapse.api.auth.Auth` to use `Requester` objects everywhere instead of user IDs. ([\#13024](https://github.com/matrix-org/synapse/issues/13024)) +- Clean-up tests for notifications. ([\#13471](https://github.com/matrix-org/synapse/issues/13471)) +- Add some miscellaneous comments to document sync, especially around `compute_state_delta`. ([\#13474](https://github.com/matrix-org/synapse/issues/13474)) +- Use literals in place of `HTTPStatus` constants in tests. ([\#13479](https://github.com/matrix-org/synapse/issues/13479), [\#13488](https://github.com/matrix-org/synapse/issues/13488)) +- Add comments about how event push actions are rotated. ([\#13485](https://github.com/matrix-org/synapse/issues/13485)) +- Modify HTML template content to better support mobile devices' screen sizes. ([\#13493](https://github.com/matrix-org/synapse/issues/13493)) +- Add a linter script which will reject non-strict types in Pydantic models. ([\#13502](https://github.com/matrix-org/synapse/issues/13502)) +- Reduce the number of tests using legacy TCP replication. ([\#13543](https://github.com/matrix-org/synapse/issues/13543)) +- Allow specifying additional request fields when using the `HomeServerTestCase.login` helper method. ([\#13549](https://github.com/matrix-org/synapse/issues/13549)) +- Make `HomeServerTestCase` load any configured homeserver modules automatically. ([\#13558](https://github.com/matrix-org/synapse/issues/13558)) + + +Synapse 1.65.0 (2022-08-16) +=========================== + +No significant changes since 1.65.0rc2. + + Synapse 1.65.0rc2 (2022-08-11) ============================== @@ -25,7 +112,7 @@ Bugfixes -------- - Update the version of the LDAP3 auth provider module included in the `matrixdotorg/synapse` DockerHub images and the Debian packages hosted on packages.matrix.org to 0.2.2. This version fixes a regression in the module. ([\#13470](https://github.com/matrix-org/synapse/issues/13470)) -- Fix a bug introduced in Synapse v1.41.0 where the `/hierarchy` API returned non-standard information (a `room_id` field under each entry in `children_state`). ([\#13365](https://github.com/matrix-org/synapse/issues/13365)) +- Fix a bug introduced in Synapse v1.41.0 where the `/hierarchy` API returned non-standard information (a `room_id` field under each entry in `children_state`) (this was reverted in v1.65.0rc2, see changelog notes above). ([\#13365](https://github.com/matrix-org/synapse/issues/13365)) - Fix a bug introduced in Synapse 0.24.0 that would respond with the wrong error status code to `/joined_members` requests when the requester is not a current member of the room. Contributed by @andrewdoh. ([\#13374](https://github.com/matrix-org/synapse/issues/13374)) - Fix bug in handling of typing events for appservices. Contributed by Nick @ Beeper (@fizzadar). ([\#13392](https://github.com/matrix-org/synapse/issues/13392)) - Fix a bug introduced in Synapse 1.57.0 where rooms listed in `exclude_rooms_from_sync` in the configuration file would not be properly excluded from incremental syncs. ([\#13408](https://github.com/matrix-org/synapse/issues/13408)) diff --git a/README.rst b/README.rst index 219e32de8e..84e5310309 100644 --- a/README.rst +++ b/README.rst @@ -2,107 +2,111 @@ Synapse |support| |development| |documentation| |license| |pypi| |python| ========================================================================= +Synapse is an open-source `Matrix <https://matrix.org/>`_ homeserver written and +maintained by the Matrix.org Foundation. We began rapid development began in 2014, +reaching v1.0.0 in 2019. Development on Synapse and the Matrix protocol itself continues +in earnest today. + +Briefly, Matrix is an open standard for communications on the internet, supporting +federation, encryption and VoIP. Matrix.org has more to say about the `goals of the +Matrix project <https://matrix.org/docs/guides/introduction>`_, and the `formal specification +<https://spec.matrix.org/>`_ describes the technical details. + .. contents:: -Introduction -============ +Installing and configuration +============================ -Matrix is an ambitious new ecosystem for open federated Instant Messaging and -VoIP. The basics you need to know to get up and running are: +The Synapse documentation describes `how to install Synapse <https://matrix-org.github.io/synapse/latest/setup/installation.html>`_. We recommend using +`Docker images <https://matrix-org.github.io/synapse/latest/setup/installation.html#docker-images-and-ansible-playbooks>`_ or `Debian packages from Matrix.org +<https://matrix-org.github.io/synapse/latest/setup/installation.html#matrixorg-packages>`_. -- Everything in Matrix happens in a room. Rooms are distributed and do not - exist on any single server. Rooms can be located using convenience aliases - like ``#matrix:matrix.org`` or ``#test:localhost:8448``. +.. _federation: -- Matrix user IDs look like ``@matthew:matrix.org`` (although in the future - you will normally refer to yourself and others using a third party identifier - (3PID): email address, phone number, etc rather than manipulating Matrix user IDs) +Synapse has a variety of `config options +<https://matrix-org.github.io/synapse/latest/usage/configuration/config_documentation.html>`_ +which can be used to customise its behaviour after installation. +There are additional details on how to `configure Synapse for federation here +<https://matrix-org.github.io/synapse/latest/federate.html>`_. -The overall architecture is:: +.. _reverse-proxy: - client <----> homeserver <=====================> homeserver <----> client - https://somewhere.org/_matrix https://elsewhere.net/_matrix +Using a reverse proxy with Synapse +---------------------------------- -``#matrix:matrix.org`` is the official support room for Matrix, and can be -accessed by any client from https://matrix.org/docs/projects/try-matrix-now.html or -via IRC bridge at irc://irc.libera.chat/matrix. +It is recommended to put a reverse proxy such as +`nginx <https://nginx.org/en/docs/http/ngx_http_proxy_module.html>`_, +`Apache <https://httpd.apache.org/docs/current/mod/mod_proxy_http.html>`_, +`Caddy <https://caddyserver.com/docs/quick-starts/reverse-proxy>`_, +`HAProxy <https://www.haproxy.org/>`_ or +`relayd <https://man.openbsd.org/relayd.8>`_ in front of Synapse. One advantage of +doing so is that it means that you can expose the default https port (443) to +Matrix clients without needing to run Synapse with root privileges. +For information on configuring one, see `the reverse proxy docs +<https://matrix-org.github.io/synapse/latest/reverse_proxy.html>`_. -Synapse is currently in rapid development, but as of version 0.5 we believe it -is sufficiently stable to be run as an internet-facing service for real usage! +Upgrading an existing Synapse +----------------------------- -About Matrix -============ +The instructions for upgrading Synapse are in `the upgrade notes`_. +Please check these instructions as upgrading may require extra steps for some +versions of Synapse. -Matrix specifies a set of pragmatic RESTful HTTP JSON APIs as an open standard, -which handle: +.. _the upgrade notes: https://matrix-org.github.io/synapse/develop/upgrade.html -- Creating and managing fully distributed chat rooms with no - single points of control or failure -- Eventually-consistent cryptographically secure synchronisation of room - state across a global open network of federated servers and services -- Sending and receiving extensible messages in a room with (optional) - end-to-end encryption -- Inviting, joining, leaving, kicking, banning room members -- Managing user accounts (registration, login, logout) -- Using 3rd Party IDs (3PIDs) such as email addresses, phone numbers, - Facebook accounts to authenticate, identify and discover users on Matrix. -- Placing 1:1 VoIP and Video calls -These APIs are intended to be implemented on a wide range of servers, services -and clients, letting developers build messaging and VoIP functionality on top -of the entirely open Matrix ecosystem rather than using closed or proprietary -solutions. The hope is for Matrix to act as the building blocks for a new -generation of fully open and interoperable messaging and VoIP apps for the -internet. +Platform dependencies +--------------------- -Synapse is a Matrix "homeserver" implementation developed by the matrix.org core -team, written in Python 3/Twisted. +Synapse uses a number of platform dependencies such as Python and PostgreSQL, +and aims to follow supported upstream versions. See the +`deprecation policy <https://matrix-org.github.io/synapse/latest/deprecation_policy.html>`_ +for more details. -In Matrix, every user runs one or more Matrix clients, which connect through to -a Matrix homeserver. The homeserver stores all their personal chat history and -user account information - much as a mail client connects through to an -IMAP/SMTP server. Just like email, you can either run your own Matrix -homeserver and control and own your own communications and history or use one -hosted by someone else (e.g. matrix.org) - there is no single point of control -or mandatory service provider in Matrix, unlike WhatsApp, Facebook, Hangouts, -etc. -We'd like to invite you to join #matrix:matrix.org (via -https://matrix.org/docs/projects/try-matrix-now.html), run a homeserver, take a look -at the `Matrix spec <https://matrix.org/docs/spec>`_, and experiment with the -`APIs <https://matrix.org/docs/api>`_ and `Client SDKs -<https://matrix.org/docs/projects/try-matrix-now.html#client-sdks>`_. +Security note +------------- -Thanks for using Matrix! +Matrix serves raw, user-supplied data in some APIs -- specifically the `content +repository endpoints`_. -Support -======= +.. _content repository endpoints: https://matrix.org/docs/spec/client_server/latest.html#get-matrix-media-r0-download-servername-mediaid -For support installing or managing Synapse, please join |room|_ (from a matrix.org -account if necessary) and ask questions there. We do not use GitHub issues for -support requests, only for bug reports and feature requests. +Whilst we make a reasonable effort to mitigate against XSS attacks (for +instance, by using `CSP`_), a Matrix homeserver should not be hosted on a +domain hosting other web applications. This especially applies to sharing +the domain with Matrix web clients and other sensitive applications like +webmail. See +https://developer.github.com/changes/2014-04-25-user-content-security for more +information. -Synapse's documentation is `nicely rendered on GitHub Pages <https://matrix-org.github.io/synapse>`_, -with its source available in |docs|_. +.. _CSP: https://github.com/matrix-org/synapse/pull/1021 -.. |room| replace:: ``#synapse:matrix.org`` -.. _room: https://matrix.to/#/#synapse:matrix.org +Ideally, the homeserver should not simply be on a different subdomain, but on +a completely different `registered domain`_ (also known as top-level site or +eTLD+1). This is because `some attacks`_ are still possible as long as the two +applications share the same registered domain. -.. |docs| replace:: ``docs`` -.. _docs: docs +.. _registered domain: https://tools.ietf.org/html/draft-ietf-httpbis-rfc6265bis-03#section-2.3 -Synapse Installation -==================== +.. _some attacks: https://en.wikipedia.org/wiki/Session_fixation#Attacks_using_cross-subdomain_cookie -.. _federation: +To illustrate this with an example, if your Element Web or other sensitive web +application is hosted on ``A.example1.com``, you should ideally host Synapse on +``example2.com``. Some amount of protection is offered by hosting on +``B.example1.com`` instead, so this is also acceptable in some scenarios. +However, you should *not* host your Synapse on ``A.example1.com``. + +Note that all of the above refers exclusively to the domain used in Synapse's +``public_baseurl`` setting. In particular, it has no bearing on the domain +mentioned in MXIDs hosted on that server. -* For details on how to install synapse, see - `Installation Instructions <https://matrix-org.github.io/synapse/latest/setup/installation.html>`_. -* For specific details on how to configure Synapse for federation see `docs/federate.md <docs/federate.md>`_ +Following this advice ensures that even if an XSS is found in Synapse, the +impact to other applications will be minimal. -Connecting to Synapse from a client -=================================== +Testing a new installation +========================== The easiest way to try out your new Synapse installation is by connecting to it from a web client. @@ -129,11 +133,20 @@ Registering a new user from a client ------------------------------------ By default, registration of new users via Matrix clients is disabled. To enable -it, specify ``enable_registration: true`` in ``homeserver.yaml``. (It is then -recommended to also set up CAPTCHA - see `<docs/CAPTCHA_SETUP.md>`_.) +it: + +1. In the + `registration config section <https://matrix-org.github.io/synapse/latest/usage/configuration/config_documentation.html#registration>`_ + set ``enable_registration: true`` in ``homeserver.yaml``. +2. Then **either**: -Once ``enable_registration`` is set to ``true``, it is possible to register a -user via a Matrix client. + a. set up a `CAPTCHA <https://matrix-org.github.io/synapse/latest/CAPTCHA_SETUP.html>`_, or + b. set ``enable_registration_without_verification: true`` in ``homeserver.yaml``. + +We **strongly** recommend using a CAPTCHA, particularly if your homeserver is exposed to +the public internet. Without it, anyone can freely register accounts on your homeserver. +This can be exploited by attackers to create spambots targetting the rest of the Matrix +federation. Your new user name will be formed partly from the ``server_name``, and partly from a localpart you specify when you create the account. Your name will take @@ -146,71 +159,22 @@ the form of:: As when logging in, you will need to specify a "Custom server". Specify your desired ``localpart`` in the 'User name' box. -Security note -============= +Troubleshooting and support +=========================== -Matrix serves raw, user-supplied data in some APIs -- specifically the `content -repository endpoints`_. +The `Admin FAQ <https://matrix-org.github.io/synapse/latest/usage/administration/admin_faq.html>`_ +includes tips on dealing with some common problems. For more details, see +`Synapse's wider documentation <https://matrix-org.github.io/synapse/latest/>`_. -.. _content repository endpoints: https://matrix.org/docs/spec/client_server/latest.html#get-matrix-media-r0-download-servername-mediaid - -Whilst we make a reasonable effort to mitigate against XSS attacks (for -instance, by using `CSP`_), a Matrix homeserver should not be hosted on a -domain hosting other web applications. This especially applies to sharing -the domain with Matrix web clients and other sensitive applications like -webmail. See -https://developer.github.com/changes/2014-04-25-user-content-security for more -information. - -.. _CSP: https://github.com/matrix-org/synapse/pull/1021 - -Ideally, the homeserver should not simply be on a different subdomain, but on -a completely different `registered domain`_ (also known as top-level site or -eTLD+1). This is because `some attacks`_ are still possible as long as the two -applications share the same registered domain. - -.. _registered domain: https://tools.ietf.org/html/draft-ietf-httpbis-rfc6265bis-03#section-2.3 - -.. _some attacks: https://en.wikipedia.org/wiki/Session_fixation#Attacks_using_cross-subdomain_cookie +For additional support installing or managing Synapse, please ask in the community +support room |room|_ (from a matrix.org account if necessary). We do not use GitHub +issues for support requests, only for bug reports and feature requests. -To illustrate this with an example, if your Element Web or other sensitive web -application is hosted on ``A.example1.com``, you should ideally host Synapse on -``example2.com``. Some amount of protection is offered by hosting on -``B.example1.com`` instead, so this is also acceptable in some scenarios. -However, you should *not* host your Synapse on ``A.example1.com``. - -Note that all of the above refers exclusively to the domain used in Synapse's -``public_baseurl`` setting. In particular, it has no bearing on the domain -mentioned in MXIDs hosted on that server. - -Following this advice ensures that even if an XSS is found in Synapse, the -impact to other applications will be minimal. - - -Upgrading an existing Synapse -============================= - -The instructions for upgrading synapse are in `the upgrade notes`_. -Please check these instructions as upgrading may require extra steps for some -versions of synapse. - -.. _the upgrade notes: https://matrix-org.github.io/synapse/develop/upgrade.html - -.. _reverse-proxy: - -Using a reverse proxy with Synapse -================================== - -It is recommended to put a reverse proxy such as -`nginx <https://nginx.org/en/docs/http/ngx_http_proxy_module.html>`_, -`Apache <https://httpd.apache.org/docs/current/mod/mod_proxy_http.html>`_, -`Caddy <https://caddyserver.com/docs/quick-starts/reverse-proxy>`_, -`HAProxy <https://www.haproxy.org/>`_ or -`relayd <https://man.openbsd.org/relayd.8>`_ in front of Synapse. One advantage of -doing so is that it means that you can expose the default https port (443) to -Matrix clients without needing to run Synapse with root privileges. +.. |room| replace:: ``#synapse:matrix.org`` +.. _room: https://matrix.to/#/#synapse:matrix.org -For information on configuring one, see `<docs/reverse_proxy.md>`_. +.. |docs| replace:: ``docs`` +.. _docs: docs Identity Servers ================ @@ -242,34 +206,15 @@ an email address with your account, or send an invite to another user via their email address. -Password reset -============== - -Users can reset their password through their client. Alternatively, a server admin -can reset a users password using the `admin API <docs/admin_api/user_admin_api.md#reset-password>`_ -or by directly editing the database as shown below. - -First calculate the hash of the new password:: - - $ ~/synapse/env/bin/hash_password - Password: - Confirm password: - $2a$12$xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx - -Then update the ``users`` table in the database:: - - UPDATE users SET password_hash='$2a$12$xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx' - WHERE name='@test:test.com'; - - -Synapse Development -=================== +Development +=========== +We welcome contributions to Synapse from the community! The best place to get started is our `guide for contributors <https://matrix-org.github.io/synapse/latest/development/contributing_guide.html>`_. This is part of our larger `documentation <https://matrix-org.github.io/synapse/latest>`_, which includes -information for synapse developers as well as synapse administrators. +information for Synapse developers as well as Synapse administrators. Developers might be particularly interested in: * `Synapse's database schema <https://matrix-org.github.io/synapse/latest/development/database_schema.html>`_, @@ -280,187 +225,6 @@ Alongside all that, join our developer community on Matrix: `#synapse-dev:matrix.org <https://matrix.to/#/#synapse-dev:matrix.org>`_, featuring real humans! -Quick start ------------ - -Before setting up a development environment for synapse, make sure you have the -system dependencies (such as the python header files) installed - see -`Platform-specific prerequisites <https://matrix-org.github.io/synapse/latest/setup/installation.html#platform-specific-prerequisites>`_. - -To check out a synapse for development, clone the git repo into a working -directory of your choice:: - - git clone https://github.com/matrix-org/synapse.git - cd synapse - -Synapse has a number of external dependencies. We maintain a fixed development -environment using `Poetry <https://python-poetry.org/>`_. First, install poetry. We recommend:: - - pip install --user pipx - pipx install poetry - -as described `here <https://python-poetry.org/docs/#installing-with-pipx>`_. -(See `poetry's installation docs <https://python-poetry.org/docs/#installation>`_ -for other installation methods.) Then ask poetry to create a virtual environment -from the project and install Synapse's dependencies:: - - poetry install --extras "all test" - -This will run a process of downloading and installing all the needed -dependencies into a virtual env. - -We recommend using the demo which starts 3 federated instances running on ports `8080` - `8082`:: - - poetry run ./demo/start.sh - -(to stop, you can use ``poetry run ./demo/stop.sh``) - -See the `demo documentation <https://matrix-org.github.io/synapse/develop/development/demo.html>`_ -for more information. - -If you just want to start a single instance of the app and run it directly:: - - # Create the homeserver.yaml config once - poetry run synapse_homeserver \ - --server-name my.domain.name \ - --config-path homeserver.yaml \ - --generate-config \ - --report-stats=[yes|no] - - # Start the app - poetry run synapse_homeserver --config-path homeserver.yaml - - -Running the unit tests ----------------------- - -After getting up and running, you may wish to run Synapse's unit tests to -check that everything is installed correctly:: - - poetry run trial tests - -This should end with a 'PASSED' result (note that exact numbers will -differ):: - - Ran 1337 tests in 716.064s - - PASSED (skips=15, successes=1322) - -For more tips on running the unit tests, like running a specific test or -to see the logging output, see the `CONTRIBUTING doc <CONTRIBUTING.md#run-the-unit-tests>`_. - - -Running the Integration Tests ------------------------------ - -Synapse is accompanied by `SyTest <https://github.com/matrix-org/sytest>`_, -a Matrix homeserver integration testing suite, which uses HTTP requests to -access the API as a Matrix client would. It is able to run Synapse directly from -the source tree, so installation of the server is not required. - -Testing with SyTest is recommended for verifying that changes related to the -Client-Server API are functioning correctly. See the `SyTest installation -instructions <https://github.com/matrix-org/sytest#installing>`_ for details. - - -Platform dependencies -===================== - -Synapse uses a number of platform dependencies such as Python and PostgreSQL, -and aims to follow supported upstream versions. See the -`<docs/deprecation_policy.md>`_ document for more details. - - -Troubleshooting -=============== - -Need help? Join our community support room on Matrix: -`#synapse:matrix.org <https://matrix.to/#/#synapse:matrix.org>`_ - -Running out of File Handles ---------------------------- - -If synapse runs out of file handles, it typically fails badly - live-locking -at 100% CPU, and/or failing to accept new TCP connections (blocking the -connecting client). Matrix currently can legitimately use a lot of file handles, -thanks to busy rooms like #matrix:matrix.org containing hundreds of participating -servers. The first time a server talks in a room it will try to connect -simultaneously to all participating servers, which could exhaust the available -file descriptors between DNS queries & HTTPS sockets, especially if DNS is slow -to respond. (We need to improve the routing algorithm used to be better than -full mesh, but as of March 2019 this hasn't happened yet). - -If you hit this failure mode, we recommend increasing the maximum number of -open file handles to be at least 4096 (assuming a default of 1024 or 256). -This is typically done by editing ``/etc/security/limits.conf`` - -Separately, Synapse may leak file handles if inbound HTTP requests get stuck -during processing - e.g. blocked behind a lock or talking to a remote server etc. -This is best diagnosed by matching up the 'Received request' and 'Processed request' -log lines and looking for any 'Processed request' lines which take more than -a few seconds to execute. Please let us know at #synapse:matrix.org if -you see this failure mode so we can help debug it, however. - -Help!! Synapse is slow and eats all my RAM/CPU! ------------------------------------------------ - -First, ensure you are running the latest version of Synapse, using Python 3 -with a PostgreSQL database. - -Synapse's architecture is quite RAM hungry currently - we deliberately -cache a lot of recent room data and metadata in RAM in order to speed up -common requests. We'll improve this in the future, but for now the easiest -way to either reduce the RAM usage (at the risk of slowing things down) -is to set the almost-undocumented ``SYNAPSE_CACHE_FACTOR`` environment -variable. The default is 0.5, which can be decreased to reduce RAM usage -in memory constrained enviroments, or increased if performance starts to -degrade. - -However, degraded performance due to a low cache factor, common on -machines with slow disks, often leads to explosions in memory use due -backlogged requests. In this case, reducing the cache factor will make -things worse. Instead, try increasing it drastically. 2.0 is a good -starting value. - -Using `libjemalloc <http://jemalloc.net/>`_ can also yield a significant -improvement in overall memory use, and especially in terms of giving back -RAM to the OS. To use it, the library must simply be put in the -LD_PRELOAD environment variable when launching Synapse. On Debian, this -can be done by installing the ``libjemalloc1`` package and adding this -line to ``/etc/default/matrix-synapse``:: - - LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libjemalloc.so.1 - -This can make a significant difference on Python 2.7 - it's unclear how -much of an improvement it provides on Python 3.x. - -If you're encountering high CPU use by the Synapse process itself, you -may be affected by a bug with presence tracking that leads to a -massive excess of outgoing federation requests (see `discussion -<https://github.com/matrix-org/synapse/issues/3971>`_). If metrics -indicate that your server is also issuing far more outgoing federation -requests than can be accounted for by your users' activity, this is a -likely cause. The misbehavior can be worked around by setting -the following in the Synapse config file: - -.. code-block:: yaml - - presence: - enabled: false - -People can't accept room invitations from me --------------------------------------------- - -The typical failure mode here is that you send an invitation to someone -to join a room or direct chat, but when they go to accept it, they get an -error (typically along the lines of "Invalid signature"). They might see -something like the following in their logs:: - - 2019-09-11 19:32:04,271 - synapse.federation.transport.server - 288 - WARNING - GET-11752 - authenticate_request failed: 401: Invalid signature for server <server> with key ed25519:a_EqML: Unable to verify signature for <server> - -This is normally caused by a misconfiguration in your reverse-proxy. See -`<docs/reverse_proxy.md>`_ and double-check that your settings are correct. - .. |support| image:: https://img.shields.io/matrix/synapse:matrix.org?label=support&logo=matrix :alt: (get support on #synapse:matrix.org) :target: https://matrix.to/#/#synapse:matrix.org diff --git a/changelog.d/13453.misc b/changelog.d/13453.misc deleted file mode 100644 index d30c5230c8..0000000000 --- a/changelog.d/13453.misc +++ /dev/null @@ -1 +0,0 @@ -Allow use of both `@trace` and `@tag_args` stacked on the same function (tracing). diff --git a/changelog.d/13459.misc b/changelog.d/13459.misc deleted file mode 100644 index e6082210a0..0000000000 --- a/changelog.d/13459.misc +++ /dev/null @@ -1 +0,0 @@ -Faster joins: update the rejected state of events during de-partial-stating. diff --git a/changelog.d/13471.misc b/changelog.d/13471.misc deleted file mode 100644 index b55ff32c76..0000000000 --- a/changelog.d/13471.misc +++ /dev/null @@ -1 +0,0 @@ -Clean-up tests for notifications. diff --git a/changelog.d/13472.doc b/changelog.d/13472.doc deleted file mode 100644 index 2ff6317300..0000000000 --- a/changelog.d/13472.doc +++ /dev/null @@ -1 +0,0 @@ -Add `openssl` example for generating registration HMAC digest. diff --git a/changelog.d/13474.misc b/changelog.d/13474.misc deleted file mode 100644 index d34c661fed..0000000000 --- a/changelog.d/13474.misc +++ /dev/null @@ -1 +0,0 @@ -Add some miscellaneous comments to document sync, especially around `compute_state_delta`. diff --git a/changelog.d/13479.misc b/changelog.d/13479.misc deleted file mode 100644 index 315930deab..0000000000 --- a/changelog.d/13479.misc +++ /dev/null @@ -1 +0,0 @@ -Use literals in place of `HTTPStatus` constants in tests. \ No newline at end of file diff --git a/changelog.d/13488.misc b/changelog.d/13488.misc deleted file mode 100644 index 315930deab..0000000000 --- a/changelog.d/13488.misc +++ /dev/null @@ -1 +0,0 @@ -Use literals in place of `HTTPStatus` constants in tests. \ No newline at end of file diff --git a/changelog.d/13492.doc b/changelog.d/13492.doc deleted file mode 100644 index fc4850d556..0000000000 --- a/changelog.d/13492.doc +++ /dev/null @@ -1 +0,0 @@ -Document that event purging related to the `redaction_retention_period` config option is executed only every 5 minutes. diff --git a/changelog.d/13493.misc b/changelog.d/13493.misc deleted file mode 100644 index d7d5c33a89..0000000000 --- a/changelog.d/13493.misc +++ /dev/null @@ -1 +0,0 @@ -Modify HTML template content to better support mobile devices' screen sizes. \ No newline at end of file diff --git a/changelog.d/13540.misc b/changelog.d/13540.misc new file mode 100644 index 0000000000..07ace50b12 --- /dev/null +++ b/changelog.d/13540.misc @@ -0,0 +1 @@ +Add experimental configuration option to allow disabling legacy Prometheus metric names. \ No newline at end of file diff --git a/changelog.d/13573.misc b/changelog.d/13573.misc new file mode 100644 index 0000000000..1ce9c0c081 --- /dev/null +++ b/changelog.d/13573.misc @@ -0,0 +1 @@ +Cache user IDs instead of profiles to reduce cache memory usage. Contributed by Nick @ Beeper (@fizzadar). diff --git a/changelog.d/13583.bugfix b/changelog.d/13583.bugfix new file mode 100644 index 0000000000..1e4ce5904b --- /dev/null +++ b/changelog.d/13583.bugfix @@ -0,0 +1 @@ +Faster Room Joins: fix `/make_knock` blocking indefinitely when the room in question is a partial-stated room. \ No newline at end of file diff --git a/changelog.d/13585.bugfix b/changelog.d/13585.bugfix new file mode 100644 index 0000000000..664b986c59 --- /dev/null +++ b/changelog.d/13585.bugfix @@ -0,0 +1 @@ +Fix loading the current stream position behind the actual position. diff --git a/changelog.d/13588.misc b/changelog.d/13588.misc new file mode 100644 index 0000000000..eca1416ceb --- /dev/null +++ b/changelog.d/13588.misc @@ -0,0 +1 @@ +Instrument `_check_sigs_and_hash_and_fetch` to trace time spent in child concurrent calls for understandable traces in Jaeger. diff --git a/changelog.d/13591.misc b/changelog.d/13591.misc new file mode 100644 index 0000000000..080e865e55 --- /dev/null +++ b/changelog.d/13591.misc @@ -0,0 +1 @@ +Improve performance of `@cachedList`. diff --git a/changelog.d/13592.misc b/changelog.d/13592.misc new file mode 100644 index 0000000000..8f48d557e5 --- /dev/null +++ b/changelog.d/13592.misc @@ -0,0 +1 @@ +Minor speed up of fetching large numbers of push rules. diff --git a/changelog.d/13597.misc b/changelog.d/13597.misc new file mode 100644 index 0000000000..eb5e971008 --- /dev/null +++ b/changelog.d/13597.misc @@ -0,0 +1 @@ + Optimise push action fetching queries. Contributed by Nick @ Beeper (@fizzadar). diff --git a/changelog.d/13600.misc b/changelog.d/13600.misc new file mode 100644 index 0000000000..1ce9c0c081 --- /dev/null +++ b/changelog.d/13600.misc @@ -0,0 +1 @@ +Cache user IDs instead of profiles to reduce cache memory usage. Contributed by Nick @ Beeper (@fizzadar). diff --git a/changelog.d/13602.doc b/changelog.d/13602.doc new file mode 100644 index 0000000000..dbba082163 --- /dev/null +++ b/changelog.d/13602.doc @@ -0,0 +1 @@ +Improve the description of the ["chain cover index"](https://matrix-org.github.io/synapse/latest/auth_chain_difference_algorithm.html) used internally by Synapse. diff --git a/changelog.d/13603.misc b/changelog.d/13603.misc new file mode 100644 index 0000000000..d08eb6cc0a --- /dev/null +++ b/changelog.d/13603.misc @@ -0,0 +1 @@ +Rename `event_map` to `unpersisted_events` when computing the auth differences. diff --git a/changelog.d/13605.misc b/changelog.d/13605.misc new file mode 100644 index 0000000000..88d518383b --- /dev/null +++ b/changelog.d/13605.misc @@ -0,0 +1 @@ +Refactor `get_users_in_room(room_id)` mis-use with dedicated `get_current_hosts_in_room(room_id)` function. diff --git a/changelog.d/13606.misc b/changelog.d/13606.misc new file mode 100644 index 0000000000..58a4467798 --- /dev/null +++ b/changelog.d/13606.misc @@ -0,0 +1 @@ +Use dedicated `get_local_users_in_room(room_id)` function to find local users when calculating `join_authorised_via_users_server` of a `/make_join` request. diff --git a/changelog.d/13608.misc b/changelog.d/13608.misc new file mode 100644 index 0000000000..19bcc45e33 --- /dev/null +++ b/changelog.d/13608.misc @@ -0,0 +1 @@ +Refactor `get_users_in_room(room_id)` mis-use to lookup single local user with dedicated `check_local_user_in_room(...)` function. diff --git a/contrib/grafana/synapse.json b/contrib/grafana/synapse.json index 819426b8ea..0f23fc17ea 100644 --- a/contrib/grafana/synapse.json +++ b/contrib/grafana/synapse.json @@ -9,17 +9,18 @@ "pluginName": "Prometheus" } ], + "__elements": {}, "__requires": [ { "type": "grafana", "id": "grafana", "name": "Grafana", - "version": "7.3.7" + "version": "9.0.4" }, { "type": "panel", "id": "graph", - "name": "Graph", + "name": "Graph (old)", "version": "" }, { @@ -33,13 +34,21 @@ "id": "prometheus", "name": "Prometheus", "version": "1.0.0" + }, + { + "type": "panel", + "id": "timeseries", + "name": "Time series", + "version": "" } ], "annotations": { "list": [ { "builtIn": 1, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "enable": false, "hide": true, "iconColor": "rgba(0, 211, 255, 1)", @@ -51,10 +60,9 @@ ] }, "editable": true, - "gnetId": null, + "fiscalYearStartMonth": 0, "graphTooltip": 0, "id": null, - "iteration": 1628606819564, "links": [ { "asDropdown": false, @@ -66,24 +74,16 @@ ], "title": "Dashboards", "type": "dashboards" - }, - { - "asDropdown": false, - "icon": "external link", - "includeVars": false, - "keepTime": false, - "tags": [], - "targetBlank": true, - "title": "Synapse Documentation", - "tooltip": "Open Documentation", - "type": "link", - "url": "https://matrix-org.github.io/synapse/latest/" } ], + "liveNow": false, "panels": [ { "collapsed": false, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, "gridPos": { "h": 1, "w": 24, @@ -92,6 +92,15 @@ }, "id": 73, "panels": [], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" + } + ], "title": "Overview", "type": "row" }, @@ -108,12 +117,8 @@ "mode": "spectrum" }, "dataFormat": "tsbuckets", - "datasource": "$datasource", - "fieldConfig": { - "defaults": { - "custom": {} - }, - "overrides": [] + "datasource": { + "uid": "$datasource" }, "gridPos": { "h": 9, @@ -132,6 +137,9 @@ "reverseYBuckets": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_http_server_response_time_seconds_bucket{servlet='RoomSendEventRestServlet',instance=\"$instance\",code=~\"2..\"}[$bucket_size])) by (le)", "format": "heatmap", "interval": "", @@ -149,31 +157,24 @@ "xAxis": { "show": true }, - "xBucketNumber": null, - "xBucketSize": null, "yAxis": { - "decimals": null, "format": "s", "logBase": 2, - "max": null, - "min": null, - "show": true, - "splitFactor": null + "show": true }, - "yBucketBound": "auto", - "yBucketNumber": null, - "yBucketSize": null + "yBucketBound": "auto" }, { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "", "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -207,7 +208,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -266,6 +267,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.99, sum(rate(synapse_http_server_response_time_seconds_bucket{servlet='RoomSendEventRestServlet',index=~\"$index\",instance=\"$instance\",code=~\"2..\"}[$bucket_size])) by (le))", "format": "time_series", "intervalFactor": 1, @@ -273,6 +277,9 @@ "refId": "D" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.9, sum(rate(synapse_http_server_response_time_seconds_bucket{servlet='RoomSendEventRestServlet',index=~\"$index\",instance=\"$instance\",code=~\"2..\"}[$bucket_size])) by (le))", "format": "time_series", "interval": "", @@ -281,6 +288,9 @@ "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.75, sum(rate(synapse_http_server_response_time_seconds_bucket{servlet='RoomSendEventRestServlet',index=~\"$index\",instance=\"$instance\",code=~\"2..\"}[$bucket_size])) by (le))", "format": "time_series", "intervalFactor": 1, @@ -288,6 +298,9 @@ "refId": "C" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.5, sum(rate(synapse_http_server_response_time_seconds_bucket{servlet='RoomSendEventRestServlet',index=~\"$index\",instance=\"$instance\",code=~\"2..\"}[$bucket_size])) by (le))", "format": "time_series", "intervalFactor": 1, @@ -295,21 +308,33 @@ "refId": "B" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.25, sum(rate(synapse_http_server_response_time_seconds_bucket{servlet='RoomSendEventRestServlet',index=~\"$index\",instance=\"$instance\",code=~\"2..\"}[$bucket_size])) by (le))", "legendFormat": "25%", "refId": "F" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.05, sum(rate(synapse_http_server_response_time_seconds_bucket{servlet='RoomSendEventRestServlet',index=~\"$index\",instance=\"$instance\",code=~\"2..\"}[$bucket_size])) by (le))", "legendFormat": "5%", "refId": "G" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_http_server_response_time_seconds_sum{servlet='RoomSendEventRestServlet',index=~\"$index\",instance=\"$instance\",code=~\"2..\"}[$bucket_size])) / sum(rate(synapse_http_server_response_time_seconds_count{servlet='RoomSendEventRestServlet',index=~\"$index\",instance=\"$instance\",code=~\"2..\"}[$bucket_size]))", "legendFormat": "Average", "refId": "H" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_storage_events_persisted_events{instance=\"$instance\"}[$bucket_size]))", "hide": false, "instant": false, @@ -319,6 +344,7 @@ ], "thresholds": [ { + "$$hashKey": "object:283", "colorMode": "warning", "fill": false, "line": true, @@ -327,6 +353,7 @@ "yaxis": "left" }, { + "$$hashKey": "object:284", "colorMode": "critical", "fill": false, "line": true, @@ -335,9 +362,7 @@ "yaxis": "left" } ], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Event Send Time Quantiles (excluding errors, all workers)", "tooltip": { "shared": true, @@ -346,34 +371,30 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "decimals": null, + "$$hashKey": "object:255", "format": "s", "label": "", "logBase": 1, - "max": null, "min": "0", "show": true }, { + "$$hashKey": "object:256", "format": "hertz", "label": "", "logBase": 1, - "max": null, "min": "0", "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -381,10 +402,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -417,7 +439,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -427,6 +449,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(process_cpu_seconds_total{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "interval": "", @@ -437,6 +462,7 @@ ], "thresholds": [ { + "$$hashKey": "object:566", "colorMode": "critical", "fill": true, "line": true, @@ -445,9 +471,7 @@ "yaxis": "left" } ], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "CPU usage", "tooltip": { "shared": false, @@ -456,34 +480,28 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "decimals": null, + "$$hashKey": "object:538", "format": "percentunit", - "label": null, "logBase": 1, "max": "1.5", "min": "0", "show": true }, { + "$$hashKey": "object:539", "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -491,12 +509,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -530,7 +549,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -540,6 +559,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "process_resident_memory_bytes{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "format": "time_series", "interval": "", @@ -550,6 +572,9 @@ "target": "" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(process_resident_memory_bytes{instance=\"$instance\",job=~\"$job\",index=~\"$index\"})", "hide": true, "interval": "", @@ -558,9 +583,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Memory", "tooltip": { "shared": false, @@ -570,31 +593,27 @@ "transformations": [], "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { + "$$hashKey": "object:1560", "format": "bytes", "logBase": 1, - "max": null, "min": "0", "show": true }, { + "$$hashKey": "object:1561", "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -602,10 +621,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -638,12 +658,13 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", "seriesOverrides": [ { + "$$hashKey": "object:639", "alias": "/max$/", "color": "#890F02", "fill": 0, @@ -655,6 +676,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "process_open_fds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "format": "time_series", "hide": false, @@ -665,6 +689,9 @@ "step": 20 }, { + "datasource": { + "uid": "$datasource" + }, "expr": "process_max_fds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "format": "time_series", "hide": true, @@ -676,9 +703,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Open FDs", "tooltip": { "shared": false, @@ -687,40 +712,35 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "decimals": null, + "$$hashKey": "object:650", "format": "none", "label": "", "logBase": 1, - "max": null, - "min": null, "show": true }, { - "decimals": null, + "$$hashKey": "object:651", "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, "gridPos": { "h": 1, "w": 24, @@ -734,12 +754,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -751,7 +772,7 @@ "h": 7, "w": 12, "x": 0, - "y": 25 + "y": 27 }, "hiddenSeries": false, "id": 5, @@ -777,15 +798,17 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", "seriesOverrides": [ { + "$$hashKey": "object:1240", "alias": "/user/" }, { + "$$hashKey": "object:1241", "alias": "/system/" } ], @@ -794,6 +817,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(process_cpu_system_seconds_total{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "intervalFactor": 1, @@ -803,6 +829,9 @@ "step": 20 }, { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(process_cpu_user_seconds_total{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "hide": false, @@ -815,6 +844,7 @@ ], "thresholds": [ { + "$$hashKey": "object:1278", "colorMode": "custom", "fillColor": "rgba(255, 255, 255, 1)", "line": true, @@ -824,6 +854,7 @@ "yaxis": "left" }, { + "$$hashKey": "object:1279", "colorMode": "custom", "fillColor": "rgba(255, 255, 255, 1)", "line": true, @@ -833,6 +864,7 @@ "yaxis": "left" }, { + "$$hashKey": "object:1498", "colorMode": "critical", "fill": true, "line": true, @@ -841,9 +873,7 @@ "yaxis": "left" } ], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "CPU", "tooltip": { "shared": false, @@ -852,15 +882,13 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "decimals": null, + "$$hashKey": "object:1250", "format": "percentunit", "label": "", "logBase": 1, @@ -869,71 +897,113 @@ "show": true }, { + "$$hashKey": "object:1251", "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "$datasource", + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, "description": "Shows the time in which the given percentage of reactor ticks completed, over the sampled timespan", "fieldConfig": { "defaults": { - "custom": {}, - "links": [] + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" }, "overrides": [] }, - "fill": 1, - "fillGradient": 0, "gridPos": { "h": 7, "w": 12, "x": 12, - "y": 25 + "y": 27 }, - "hiddenSeries": false, "id": 105, "interval": "", - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, "links": [], - "nullPointMode": "null", "options": { - "alertThreshold": true + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom" + }, + "tooltip": { + "mode": "single", + "sort": "none" + } }, - "paceLength": 10, - "percentage": false, - "pluginVersion": "7.3.7", - "pointradius": 5, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, + "pluginVersion": "8.3.2", "targets": [ { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, + "expr": "histogram_quantile(0.999, rate(python_twisted_reactor_tick_time_bucket{index=~\"$index\",instance=\"$instance\",job=~\"$job\"}[$bucket_size]))", + "hide": false, + "interval": "", + "legendFormat": "{{job}}-{{index}} 99.9%", + "refId": "E" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, "expr": "histogram_quantile(0.99, rate(python_twisted_reactor_tick_time_bucket{index=~\"$index\",instance=\"$instance\",job=~\"$job\"}[$bucket_size]))", "format": "time_series", "interval": "", @@ -943,13 +1013,23 @@ "step": 20 }, { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, "expr": "histogram_quantile(0.95, rate(python_twisted_reactor_tick_time_bucket{index=~\"$index\",instance=\"$instance\",job=~\"$job\"}[$bucket_size]))", "format": "time_series", + "interval": "", "intervalFactor": 1, "legendFormat": "{{job}}-{{index}} 95%", "refId": "B" }, { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, "expr": "histogram_quantile(0.90, rate(python_twisted_reactor_tick_time_bucket{index=~\"$index\",instance=\"$instance\",job=~\"$job\"}[$bucket_size]))", "format": "time_series", "intervalFactor": 1, @@ -957,6 +1037,10 @@ "refId": "C" }, { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, "expr": "rate(python_twisted_reactor_tick_time_sum{index=~\"$index\",instance=\"$instance\",job=~\"$job\"}[$bucket_size]) / rate(python_twisted_reactor_tick_time_count{index=~\"$index\",instance=\"$instance\",job=~\"$job\"}[$bucket_size])", "format": "time_series", "intervalFactor": 1, @@ -964,58 +1048,21 @@ "refId": "D" } ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, "title": "Reactor tick quantiles", - "tooltip": { - "shared": false, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "s", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": false - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } + "type": "timeseries" }, { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -1027,7 +1074,7 @@ "h": 7, "w": 12, "x": 0, - "y": 32 + "y": 34 }, "hiddenSeries": false, "id": 34, @@ -1049,7 +1096,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -1059,6 +1106,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "process_resident_memory_bytes{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "format": "time_series", "interval": "", @@ -1069,6 +1119,9 @@ "target": "" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(process_resident_memory_bytes{instance=\"$instance\",job=~\"$job\",index=~\"$index\"})", "interval": "", "legendFormat": "total", @@ -1076,9 +1129,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Memory", "tooltip": { "shared": false, @@ -1088,9 +1139,7 @@ "transformations": [], "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -1098,21 +1147,17 @@ { "format": "bytes", "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -1120,10 +1165,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -1134,7 +1180,7 @@ "h": 7, "w": 12, "x": 12, - "y": 32 + "y": 34 }, "hiddenSeries": false, "id": 49, @@ -1156,7 +1202,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -1172,6 +1218,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "scrape_duration_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "format": "time_series", "interval": "", @@ -1182,9 +1231,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Prometheus scrape time", "tooltip": { "shared": false, @@ -1193,18 +1240,14 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "s", - "label": null, "logBase": 1, - "max": null, "min": "0", "show": true }, @@ -1219,8 +1262,7 @@ } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -1228,10 +1270,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -1242,7 +1285,7 @@ "h": 7, "w": 12, "x": 0, - "y": 39 + "y": 41 }, "hiddenSeries": false, "id": 53, @@ -1264,7 +1307,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -1274,6 +1317,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "min_over_time(up{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "intervalFactor": 2, @@ -1282,9 +1328,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Up", "tooltip": { "shared": false, @@ -1293,33 +1337,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -1327,10 +1362,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -1341,7 +1377,7 @@ "h": 7, "w": 12, "x": 12, - "y": 39 + "y": 41 }, "hiddenSeries": false, "id": 120, @@ -1362,7 +1398,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 2, "points": false, "renderer": "flot", @@ -1372,6 +1408,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_http_server_response_ru_utime_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])+rate(synapse_http_server_response_ru_stime_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "hide": false, @@ -1381,6 +1420,9 @@ "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_background_process_ru_utime_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])+rate(synapse_background_process_ru_stime_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "hide": false, @@ -1401,9 +1443,7 @@ "yaxis": "left" } ], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Stacked CPU usage", "tooltip": { "shared": false, @@ -1412,33 +1452,26 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { + "$$hashKey": "object:572", "format": "percentunit", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { + "$$hashKey": "object:573", "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -1446,10 +1479,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -1460,7 +1494,7 @@ "h": 7, "w": 12, "x": 0, - "y": 46 + "y": 48 }, "hiddenSeries": false, "id": 136, @@ -1481,7 +1515,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 2, "points": false, "renderer": "flot", @@ -1491,20 +1525,24 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_http_client_requests{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "legendFormat": "{{job}}-{{index}} {{method}}", "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_http_matrixfederationclient_requests{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "legendFormat": "{{job}}-{{index}} {{method}} (federation)", "refId": "B" } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Outgoing HTTP request rate", "tooltip": { "shared": false, @@ -1513,43 +1551,133 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "reqps", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "active threads", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 48 + }, + "id": 207, + "options": { + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom" + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, + "expr": "synapse_threadpool_working_threads{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", + "interval": "", + "legendFormat": "{{job}}-{{index}} {{name}}", + "refId": "A" + } + ], + "title": "Threadpool activity", + "type": "timeseries" + } + ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "refId": "A" } ], - "repeat": null, "title": "Process info", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, "gridPos": { "h": 1, "w": 24, @@ -1571,18 +1699,14 @@ "mode": "spectrum" }, "dataFormat": "tsbuckets", - "datasource": "$datasource", - "fieldConfig": { - "defaults": { - "custom": {} - }, - "overrides": [] + "datasource": { + "uid": "$datasource" }, "gridPos": { "h": 9, "w": 12, "x": 0, - "y": 21 + "y": 28 }, "heatmap": {}, "hideZeroBuckets": false, @@ -1595,6 +1719,9 @@ "reverseYBuckets": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_http_server_response_time_seconds_bucket{servlet='RoomSendEventRestServlet',instance=\"$instance\"}[$bucket_size])) by (le)", "format": "heatmap", "intervalFactor": 1, @@ -1611,33 +1738,26 @@ "xAxis": { "show": true }, - "xBucketNumber": null, - "xBucketSize": null, "yAxis": { - "decimals": null, "format": "s", "logBase": 2, - "max": null, - "min": null, - "show": true, - "splitFactor": null + "show": true }, - "yBucketBound": "auto", - "yBucketNumber": null, - "yBucketSize": null + "yBucketBound": "auto" }, { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "", "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -1649,7 +1769,7 @@ "h": 9, "w": 12, "x": 12, - "y": 21 + "y": 28 }, "hiddenSeries": false, "id": 33, @@ -1671,7 +1791,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -1681,6 +1801,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_storage_events_persisted_events{instance=\"$instance\"}[$bucket_size])) without (job,index)", "format": "time_series", "interval": "", @@ -1692,9 +1815,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Events Persisted (all workers)", "tooltip": { "shared": true, @@ -1703,31 +1824,26 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { + "$$hashKey": "object:102", "format": "hertz", "logBase": 1, - "max": null, - "min": null, "show": true }, { + "$$hashKey": "object:103", "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -1735,21 +1851,17 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", - "decimals": 1, - "fieldConfig": { - "defaults": { - "custom": {} - }, - "overrides": [] + "datasource": { + "uid": "$datasource" }, + "decimals": 1, "fill": 1, "fillGradient": 0, "gridPos": { "h": 7, "w": 12, "x": 0, - "y": 30 + "y": 37 }, "hiddenSeries": false, "id": 40, @@ -1770,7 +1882,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -1780,6 +1892,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_storage_events_persisted_by_source_type{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "intervalFactor": 2, @@ -1788,9 +1903,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Events/s Local vs Remote", "tooltip": { "shared": true, @@ -1799,9 +1912,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -1810,22 +1921,17 @@ "format": "hertz", "label": "", "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -1833,21 +1939,17 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", - "decimals": 1, - "fieldConfig": { - "defaults": { - "custom": {} - }, - "overrides": [] + "datasource": { + "uid": "$datasource" }, + "decimals": 1, "fill": 1, "fillGradient": 0, "gridPos": { "h": 7, "w": 12, "x": 12, - "y": 30 + "y": 37 }, "hiddenSeries": false, "id": 46, @@ -1868,7 +1970,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -1878,6 +1980,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_storage_events_persisted_by_event_type{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "format": "time_series", "instant": false, @@ -1888,9 +1993,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Events/s by Type", "tooltip": { "shared": false, @@ -1899,33 +2002,25 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -1935,21 +2030,17 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", - "decimals": 1, - "fieldConfig": { - "defaults": { - "custom": {} - }, - "overrides": [] + "datasource": { + "uid": "$datasource" }, + "decimals": 1, "fill": 1, "fillGradient": 0, "gridPos": { "h": 7, "w": 12, "x": 0, - "y": 37 + "y": 44 }, "hiddenSeries": false, "id": 44, @@ -1973,7 +2064,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -1983,6 +2074,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_storage_events_persisted_by_origin{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "format": "time_series", "intervalFactor": 2, @@ -1992,9 +2086,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Events/s by Origin", "tooltip": { "shared": false, @@ -2003,33 +2095,25 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -2037,21 +2121,17 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", - "decimals": 1, - "fieldConfig": { - "defaults": { - "custom": {} - }, - "overrides": [] + "datasource": { + "uid": "$datasource" }, + "decimals": 1, "fill": 1, "fillGradient": 0, "gridPos": { "h": 7, "w": 12, "x": 12, - "y": 37 + "y": 44 }, "hiddenSeries": false, "id": 45, @@ -2075,7 +2155,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -2085,6 +2165,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_storage_events_persisted_events_sep{job=~\"$job\",index=~\"$index\", type=\"m.room.member\",instance=\"$instance\", origin_type=\"local\"}[$bucket_size])) by (origin_type, origin_entity)", "format": "time_series", "intervalFactor": 2, @@ -2094,9 +2177,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Memberships/s by Origin", "tooltip": { "shared": true, @@ -2105,33 +2186,25 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -2139,10 +2212,12 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -2153,7 +2228,7 @@ "h": 9, "w": 12, "x": 0, - "y": 44 + "y": 51 }, "hiddenSeries": false, "id": 118, @@ -2175,7 +2250,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -2191,6 +2266,11 @@ "steppedLine": false, "targets": [ { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, "expr": "histogram_quantile(0.99, sum(rate(synapse_http_server_response_time_seconds_bucket{servlet='RoomSendEventRestServlet',instance=\"$instance\",code=~\"2..\",job=~\"$job\",index=~\"$index\"}[$bucket_size])) without (method))", "format": "time_series", "interval": "", @@ -2199,6 +2279,10 @@ "refId": "A" }, { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, "expr": "histogram_quantile(0.95, sum(rate(synapse_http_server_response_time_seconds_bucket{servlet='RoomSendEventRestServlet',instance=\"$instance\",code=~\"2..\",job=~\"$job\",index=~\"$index\"}[$bucket_size])) without (method))", "format": "time_series", "interval": "", @@ -2207,6 +2291,10 @@ "refId": "B" }, { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, "expr": "histogram_quantile(0.90, sum(rate(synapse_http_server_response_time_seconds_bucket{servlet='RoomSendEventRestServlet',instance=\"$instance\",code=~\"2..\",job=~\"$job\",index=~\"$index\"}[$bucket_size])) without (method))", "format": "time_series", "intervalFactor": 1, @@ -2214,6 +2302,10 @@ "refId": "C" }, { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, "expr": "histogram_quantile(0.50, sum(rate(synapse_http_server_response_time_seconds_bucket{servlet='RoomSendEventRestServlet',instance=\"$instance\",code=~\"2..\",job=~\"$job\",index=~\"$index\"}[$bucket_size])) without (method))", "format": "time_series", "intervalFactor": 1, @@ -2221,6 +2313,10 @@ "refId": "D" }, { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, "expr": "sum(rate(synapse_http_server_response_time_seconds_sum{servlet='RoomSendEventRestServlet',instance=\"$instance\",code=~\"2..\",job=~\"$job\",index=~\"$index\"}[$bucket_size])) without (method) / sum(rate(synapse_http_server_response_time_seconds_count{servlet='RoomSendEventRestServlet',instance=\"$instance\",code=~\"2..\",job=~\"$job\",index=~\"$index\"}[$bucket_size])) without (method)", "format": "time_series", "intervalFactor": 1, @@ -2229,9 +2325,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Event send time quantiles by worker", "tooltip": { "shared": true, @@ -2240,43 +2334,154 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { + "$$hashKey": "object:263", "format": "s", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { + "$$hashKey": "object:264", "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "description": "CPU and DB time spent on most expensive state resolution in a room, summed over all workers. This is a very rough proxy for \"how fast is state res\", but it doesn't accurately represent the system load (e.g. it completely ignores cheap state resolutions).\n", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 30, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s/s" + }, + "overrides": [] + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 51 + }, + "id": 222, + "options": { + "legend": { + "calcs": [], + "displayMode": "hidden", + "placement": "bottom" + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "exemplar": false, + "expr": "sum(rate(synapse_state_res_db_for_biggest_room_seconds{instance=\"$instance\"}[1m]))", + "format": "time_series", + "hide": false, + "instant": false, + "interval": "", + "legendFormat": "DB time", + "refId": "B" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "exemplar": false, + "expr": "sum(rate(synapse_state_res_cpu_for_biggest_room_seconds{instance=\"$instance\"}[1m]))", + "format": "time_series", + "hide": false, + "instant": false, + "interval": "", + "legendFormat": "CPU time", + "refId": "C" + } + ], + "title": "Stateres worst-case", + "type": "timeseries" + } + ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "refId": "A" } ], - "repeat": null, "title": "Event persistence", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, "gridPos": { "h": 1, "w": 24, @@ -2290,13 +2495,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", - "decimals": null, + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -2308,7 +2513,7 @@ "h": 8, "w": 12, "x": 0, - "y": 31 + "y": 29 }, "hiddenSeries": false, "id": 4, @@ -2333,7 +2538,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -2343,6 +2548,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_http_server_requests_received{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "interval": "", @@ -2370,9 +2578,7 @@ "yaxis": "left" } ], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Request Count by arrival time", "tooltip": { "shared": false, @@ -2381,9 +2587,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -2391,21 +2595,16 @@ { "format": "hertz", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -2413,12 +2612,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -2430,7 +2630,7 @@ "h": 8, "w": 12, "x": 12, - "y": 31 + "y": 29 }, "hiddenSeries": false, "id": 32, @@ -2451,7 +2651,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -2461,6 +2661,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_http_server_requests_received{instance=\"$instance\",job=~\"$job\",index=~\"$index\",method!=\"OPTIONS\"}[$bucket_size]) and topk(10,synapse_http_server_requests_received{instance=\"$instance\",job=~\"$job\",method!=\"OPTIONS\"})", "format": "time_series", "intervalFactor": 2, @@ -2471,9 +2674,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Top 10 Request Counts", "tooltip": { "shared": false, @@ -2482,9 +2683,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -2492,21 +2691,16 @@ { "format": "hertz", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -2514,13 +2708,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", - "decimals": null, + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -2532,7 +2726,7 @@ "h": 8, "w": 12, "x": 0, - "y": 39 + "y": 37 }, "hiddenSeries": false, "id": 139, @@ -2557,7 +2751,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -2567,6 +2761,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_http_server_in_flight_requests_ru_utime_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])+rate(synapse_http_server_in_flight_requests_ru_stime_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "interval": "", @@ -2594,9 +2791,7 @@ "yaxis": "left" } ], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Total CPU Usage by Endpoint", "tooltip": { "shared": false, @@ -2605,9 +2800,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -2615,21 +2808,16 @@ { "format": "percentunit", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -2637,13 +2825,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", - "decimals": null, + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -2655,7 +2843,7 @@ "h": 8, "w": 12, "x": 12, - "y": 39 + "y": 37 }, "hiddenSeries": false, "id": 52, @@ -2680,7 +2868,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -2690,6 +2878,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "(rate(synapse_http_server_in_flight_requests_ru_utime_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])+rate(synapse_http_server_in_flight_requests_ru_stime_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])) / rate(synapse_http_server_requests_received{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "interval": "", @@ -2717,9 +2908,7 @@ "yaxis": "left" } ], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Average CPU Usage by Endpoint", "tooltip": { "shared": false, @@ -2728,9 +2917,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -2738,21 +2925,16 @@ { "format": "s", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -2760,12 +2942,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -2777,7 +2960,7 @@ "h": 8, "w": 12, "x": 0, - "y": 47 + "y": 45 }, "hiddenSeries": false, "id": 7, @@ -2801,7 +2984,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -2811,6 +2994,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_http_server_in_flight_requests_db_txn_duration_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "interval": "", @@ -2821,9 +3007,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "DB Usage by endpoint", "tooltip": { "shared": false, @@ -2832,9 +3016,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -2842,21 +3024,16 @@ { "format": "percentunit", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -2864,13 +3041,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", - "decimals": null, + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -2882,7 +3059,7 @@ "h": 8, "w": 12, "x": 12, - "y": 47 + "y": 45 }, "hiddenSeries": false, "id": 47, @@ -2907,7 +3084,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -2917,6 +3094,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "(sum(rate(synapse_http_server_response_time_seconds_sum{instance=\"$instance\",job=~\"$job\",index=~\"$index\",tag!=\"incremental_sync\"}[$bucket_size])) without (code))/(sum(rate(synapse_http_server_response_time_seconds_count{instance=\"$instance\",job=~\"$job\",index=~\"$index\",tag!=\"incremental_sync\"}[$bucket_size])) without (code))", "format": "time_series", "hide": false, @@ -2928,9 +3108,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Non-sync avg response time", "tooltip": { "shared": false, @@ -2939,9 +3117,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -2949,21 +3125,16 @@ { "format": "s", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": false } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -2971,10 +3142,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -2985,7 +3157,7 @@ "h": 9, "w": 12, "x": 0, - "y": 55 + "y": 53 }, "hiddenSeries": false, "id": 103, @@ -3006,7 +3178,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -3023,6 +3195,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "topk(10,synapse_http_server_in_flight_requests_count{instance=\"$instance\",job=~\"$job\",index=~\"$index\"})", "format": "time_series", "interval": "", @@ -3031,6 +3206,9 @@ "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(avg_over_time(synapse_http_server_in_flight_requests_count{job=\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size]))", "interval": "", "legendFormat": "Total", @@ -3038,9 +3216,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Requests in flight", "tooltip": { "shared": false, @@ -3049,43 +3225,45 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], - "repeat": null, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "refId": "A" + } + ], "title": "Requests", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, "gridPos": { "h": 1, "w": 24, @@ -3099,10 +3277,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -3113,7 +3292,7 @@ "h": 9, "w": 12, "x": 0, - "y": 32 + "y": 5 }, "hiddenSeries": false, "id": 99, @@ -3130,9 +3309,12 @@ "linewidth": 1, "links": [], "nullPointMode": "null", + "options": { + "alertThreshold": true + }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.1.3", + "pluginVersion": "8.4.3", "pointradius": 5, "points": false, "renderer": "flot", @@ -3142,6 +3324,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_background_process_ru_utime_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])+rate(synapse_background_process_ru_stime_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "interval": "", @@ -3151,9 +3336,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "CPU usage by background jobs", "tooltip": { "shared": false, @@ -3162,33 +3345,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "percentunit", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -3196,10 +3370,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -3210,7 +3385,7 @@ "h": 9, "w": 12, "x": 12, - "y": 32 + "y": 5 }, "hiddenSeries": false, "id": 101, @@ -3227,9 +3402,12 @@ "linewidth": 1, "links": [], "nullPointMode": "null", + "options": { + "alertThreshold": true + }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.1.3", + "pluginVersion": "8.4.3", "pointradius": 5, "points": false, "renderer": "flot", @@ -3239,6 +3417,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_background_process_db_txn_duration_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]) + rate(synapse_background_process_db_sched_duration_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "hide": false, @@ -3248,9 +3429,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "DB usage by background jobs (including scheduling time)", "tooltip": { "shared": false, @@ -3259,33 +3438,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "percentunit", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -3293,10 +3463,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -3307,7 +3478,7 @@ "h": 8, "w": 12, "x": 0, - "y": 41 + "y": 14 }, "hiddenSeries": false, "id": 138, @@ -3323,8 +3494,11 @@ "lines": true, "linewidth": 1, "nullPointMode": "null", + "options": { + "alertThreshold": true + }, "percentage": false, - "pluginVersion": "7.1.3", + "pluginVersion": "8.4.3", "pointradius": 2, "points": false, "renderer": "flot", @@ -3334,15 +3508,16 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_background_process_in_flight_count{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}", "legendFormat": "{{job}}-{{index}} {{name}}", "refId": "A" } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Background jobs in flight", "tooltip": { "shared": false, @@ -3351,42 +3526,45 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "refId": "A" + } + ], "title": "Background jobs", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, "gridPos": { "h": 1, "w": 24, @@ -3400,10 +3578,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -3436,7 +3615,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.4.3", "pointradius": 5, "points": false, "renderer": "flot", @@ -3446,6 +3625,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_federation_client_sent_transactions{instance=\"$instance\"}[$bucket_size]))", "format": "time_series", "intervalFactor": 1, @@ -3453,15 +3635,16 @@ "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_util_metrics_block_count{block_name=\"_send_new_transaction\",instance=\"$instance\"}[$bucket_size]) - ignoring (block_name) rate(synapse_federation_client_sent_transactions{instance=\"$instance\"}[$bucket_size]))", "legendFormat": "failed txn rate", "refId": "B" } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Outgoing federation transaction rate", "tooltip": { "shared": true, @@ -3470,33 +3653,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -3504,10 +3678,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -3540,7 +3715,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.4.3", "pointradius": 5, "points": false, "renderer": "flot", @@ -3550,6 +3725,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_federation_server_received_pdus{instance=~\"$instance\"}[$bucket_size]))", "format": "time_series", "intervalFactor": 1, @@ -3557,6 +3735,9 @@ "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_federation_server_received_edus{instance=~\"$instance\"}[$bucket_size]))", "format": "time_series", "intervalFactor": 1, @@ -3565,9 +3746,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Incoming PDU/EDU rate", "tooltip": { "shared": true, @@ -3576,33 +3755,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -3610,10 +3780,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -3646,7 +3817,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.4.3", "pointradius": 5, "points": false, "renderer": "flot", @@ -3656,6 +3827,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_federation_client_sent_pdu_destinations:total{instance=\"$instance\"}[$bucket_size]))", "format": "time_series", "interval": "", @@ -3664,6 +3838,9 @@ "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_federation_client_sent_edus{instance=\"$instance\"}[$bucket_size]))", "format": "time_series", "intervalFactor": 1, @@ -3672,9 +3849,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Outgoing PDU/EDU rate", "tooltip": { "shared": true, @@ -3683,33 +3858,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -3717,10 +3883,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -3753,7 +3920,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.4.3", "pointradius": 5, "points": false, "renderer": "flot", @@ -3763,6 +3930,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_federation_client_sent_edus_by_type{instance=\"$instance\"}[$bucket_size])", "format": "time_series", "interval": "", @@ -3772,9 +3942,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Outgoing EDUs by type", "tooltip": { "shared": true, @@ -3783,33 +3951,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -3817,11 +3976,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, "description": "The number of events in the in-memory queues ", "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -3852,7 +4013,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.4.3", "pointradius": 2, "points": false, "renderer": "flot", @@ -3862,12 +4023,20 @@ "steppedLine": false, "targets": [ { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, "expr": "synapse_federation_transaction_queue_pending_pdus{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "interval": "", "legendFormat": "pending PDUs {{job}}-{{index}}", "refId": "A" }, { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, "expr": "synapse_federation_transaction_queue_pending_edus{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "interval": "", "legendFormat": "pending EDUs {{job}}-{{index}}", @@ -3875,9 +4044,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "In-memory federation transmission queues", "tooltip": { "shared": true, @@ -3886,9 +4053,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -3897,7 +4062,6 @@ "format": "short", "label": "events", "logBase": 1, - "max": null, "min": "0", "show": true }, @@ -3905,14 +4069,11 @@ "format": "short", "label": "", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -3920,11 +4081,12 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "Number of events queued up on the master process for processing by the federation sender", "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -3957,7 +4119,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.4.3", "pointradius": 5, "points": false, "renderer": "flot", @@ -3967,6 +4129,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_federation_send_queue_presence_changed_size{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "format": "time_series", "interval": "", @@ -3975,6 +4140,9 @@ "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_federation_send_queue_presence_map_size{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "format": "time_series", "hide": false, @@ -3984,6 +4152,9 @@ "refId": "B" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_federation_send_queue_presence_destinations_size{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "format": "time_series", "hide": false, @@ -3993,6 +4164,9 @@ "refId": "E" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_federation_send_queue_keyed_edu_size{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "format": "time_series", "hide": false, @@ -4002,6 +4176,9 @@ "refId": "C" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_federation_send_queue_edus_size{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "format": "time_series", "hide": false, @@ -4011,6 +4188,9 @@ "refId": "D" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_federation_send_queue_pos_time_size{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "format": "time_series", "hide": false, @@ -4021,9 +4201,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Outgoing EDU queues on master", "tooltip": { "shared": true, @@ -4032,39 +4210,30 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "none", - "label": null, "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { "cards": { - "cardPadding": -1, - "cardRound": null + "cardPadding": -1 }, "color": { "cardColor": "#b4ff00", @@ -4075,12 +4244,8 @@ "mode": "spectrum" }, "dataFormat": "tsbuckets", - "datasource": "$datasource", - "fieldConfig": { - "defaults": { - "custom": {} - }, - "overrides": [] + "datasource": { + "uid": "$datasource" }, "gridPos": { "h": 9, @@ -4099,6 +4264,9 @@ "reverseYBuckets": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_event_processing_lag_by_event_bucket{instance=\"$instance\",name=\"federation_sender\"}[$bucket_size])) by (le)", "format": "heatmap", "instant": false, @@ -4118,30 +4286,24 @@ "xAxis": { "show": true }, - "xBucketNumber": null, - "xBucketSize": null, "yAxis": { "decimals": 0, "format": "s", "logBase": 1, - "max": null, - "min": null, - "show": true, - "splitFactor": null + "show": true }, - "yBucketBound": "auto", - "yBucketNumber": null, - "yBucketSize": null + "yBucketBound": "auto" }, { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -4175,7 +4337,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.4.3", "pointradius": 5, "points": false, "renderer": "flot", @@ -4226,6 +4388,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.99, sum(rate(synapse_event_processing_lag_by_event_bucket{name='federation_sender',index=~\"$index\",instance=\"$instance\"}[$bucket_size])) by (le))", "format": "time_series", "interval": "", @@ -4234,6 +4399,9 @@ "refId": "D" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.9, sum(rate(synapse_event_processing_lag_by_event_bucket{name='federation_sender',index=~\"$index\",instance=\"$instance\"}[$bucket_size])) by (le))", "format": "time_series", "interval": "", @@ -4242,6 +4410,9 @@ "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.75, sum(rate(synapse_event_processing_lag_by_event_bucket{name='federation_sender',index=~\"$index\",instance=\"$instance\"}[$bucket_size])) by (le))", "format": "time_series", "interval": "", @@ -4250,6 +4421,9 @@ "refId": "C" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.5, sum(rate(synapse_event_processing_lag_by_event_bucket{name='federation_sender',index=~\"$index\",instance=\"$instance\"}[$bucket_size])) by (le))", "format": "time_series", "interval": "", @@ -4258,18 +4432,27 @@ "refId": "B" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.25, sum(rate(synapse_event_processing_lag_by_event_bucket{name='federation_sender',index=~\"$index\",instance=\"$instance\"}[$bucket_size])) by (le))", "interval": "", "legendFormat": "25%", "refId": "F" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.05, sum(rate(synapse_event_processing_lag_by_event_bucket{name='federation_sender',index=~\"$index\",instance=\"$instance\"}[$bucket_size])) by (le))", "interval": "", "legendFormat": "5%", "refId": "G" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_event_processing_lag_by_event_sum{name='federation_sender',index=~\"$index\",instance=\"$instance\"}[$bucket_size])) / sum(rate(synapse_event_processing_lag_by_event_count{name='federation_sender',index=~\"$index\",instance=\"$instance\"}[$bucket_size]))", "interval": "", "legendFormat": "Average", @@ -4294,9 +4477,7 @@ "yaxis": "left" } ], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Federation send PDU lag quantiles", "tooltip": { "shared": true, @@ -4305,19 +4486,15 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "decimals": null, "format": "s", "label": "", "logBase": 1, - "max": null, "min": "0", "show": true }, @@ -4325,20 +4502,17 @@ "format": "hertz", "label": "", "logBase": 1, - "max": null, "min": "0", "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { "cards": { - "cardPadding": -1, - "cardRound": null + "cardPadding": -1 }, "color": { "cardColor": "#b4ff00", @@ -4349,12 +4523,8 @@ "mode": "spectrum" }, "dataFormat": "tsbuckets", - "datasource": "$datasource", - "fieldConfig": { - "defaults": { - "custom": {} - }, - "overrides": [] + "datasource": { + "uid": "$datasource" }, "gridPos": { "h": 9, @@ -4373,6 +4543,9 @@ "reverseYBuckets": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_federation_server_pdu_process_time_bucket{instance=\"$instance\"}[$bucket_size])) by (le)", "format": "heatmap", "instant": false, @@ -4392,32 +4565,26 @@ "xAxis": { "show": true }, - "xBucketNumber": null, - "xBucketSize": null, "yAxis": { "decimals": 0, "format": "s", "logBase": 1, - "max": null, - "min": null, - "show": true, - "splitFactor": null + "show": true }, - "yBucketBound": "auto", - "yBucketNumber": null, - "yBucketSize": null + "yBucketBound": "auto" }, { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -4451,7 +4618,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.4.3", "pointradius": 5, "points": false, "renderer": "flot", @@ -4461,6 +4628,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_federation_server_oldest_inbound_pdu_in_staging{job=\"$job\",index=~\"$index\",instance=\"$instance\"}", "format": "time_series", "interval": "", @@ -4471,9 +4641,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Age of oldest event in staging area", "tooltip": { "msResolution": false, @@ -4483,33 +4651,27 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { + "$$hashKey": "object:92", "format": "ms", - "label": null, "logBase": 1, - "max": null, "min": 0, "show": true }, { + "$$hashKey": "object:93", "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -4517,12 +4679,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -4556,7 +4719,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.4.3", "pointradius": 5, "points": false, "renderer": "flot", @@ -4566,6 +4729,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_federation_server_number_inbound_pdu_in_staging{job=\"$job\",index=~\"$index\",instance=\"$instance\"}", "format": "time_series", "interval": "", @@ -4576,9 +4742,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Number of events in federation staging area", "tooltip": { "msResolution": false, @@ -4588,33 +4752,27 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { + "$$hashKey": "object:92", "format": "none", - "label": null, "logBase": 1, - "max": null, "min": 0, "show": true }, { + "$$hashKey": "object:93", "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -4622,12 +4780,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "${DS_PROMETHEUS}", - "fieldConfig": { - "defaults": { - "custom": {} - }, - "overrides": [] + "datasource": { + "type": "prometheus", + "uid": "$datasource" }, "fill": 1, "fillGradient": 0, @@ -4655,7 +4810,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.4.3", "pointradius": 2, "points": false, "renderer": "flot", @@ -4665,6 +4820,10 @@ "steppedLine": false, "targets": [ { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, "expr": "sum(rate(synapse_federation_soft_failed_events_total{instance=\"$instance\"}[$bucket_size]))", "interval": "", "legendFormat": "soft-failed events", @@ -4672,9 +4831,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Soft-failed event rate", "tooltip": { "shared": true, @@ -4683,42 +4840,47 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { + "$$hashKey": "object:131", "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { + "$$hashKey": "object:132", "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": false } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "refId": "A" + } + ], "title": "Federation", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, "gridPos": { "h": 1, "w": 24, @@ -4732,10 +4894,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -4746,7 +4909,7 @@ "h": 8, "w": 12, "x": 0, - "y": 34 + "y": 32 }, "hiddenSeries": false, "id": 51, @@ -4763,9 +4926,12 @@ "linewidth": 1, "links": [], "nullPointMode": "null", + "options": { + "alertThreshold": true + }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.1.3", + "pluginVersion": "8.4.3", "pointradius": 5, "points": false, "renderer": "flot", @@ -4775,6 +4941,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_http_httppusher_http_pushes_processed{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]) and on (instance, job, index) (synapse_http_httppusher_http_pushes_failed + synapse_http_httppusher_http_pushes_processed) > 0", "format": "time_series", "interval": "", @@ -4784,6 +4953,9 @@ "step": 20 }, { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_http_httppusher_http_pushes_failed{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]) and on (instance, job, index) (synapse_http_httppusher_http_pushes_failed + synapse_http_httppusher_http_pushes_processed) > 0", "format": "time_series", "intervalFactor": 2, @@ -4793,9 +4965,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "HTTP Push rate", "tooltip": { "shared": true, @@ -4804,33 +4974,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -4838,11 +4999,12 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "", "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -4853,7 +5015,7 @@ "h": 8, "w": 12, "x": 12, - "y": 34 + "y": 32 }, "hiddenSeries": false, "id": 134, @@ -4870,8 +5032,11 @@ "lines": true, "linewidth": 1, "nullPointMode": "null", + "options": { + "alertThreshold": true + }, "percentage": false, - "pluginVersion": "7.1.3", + "pluginVersion": "8.4.3", "pointradius": 2, "points": false, "renderer": "flot", @@ -4881,15 +5046,16 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "topk(10,synapse_pushers{job=~\"$job\",index=~\"$index\", instance=\"$instance\"})", "legendFormat": "{{kind}} {{app_id}}", "refId": "A" } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Active pusher instances by app", "tooltip": { "shared": false, @@ -4898,60 +5064,65 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], - "repeat": null, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "refId": "A" + } + ], "title": "Pushes", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 32 }, - "id": 58, + "id": 219, "panels": [ { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "How many entries in current state that we are iterating over while calculating push rules.", "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -4965,6 +5136,598 @@ "y": 33 }, "hiddenSeries": false, + "id": 209, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "alertThreshold": true + }, + "paceLength": 10, + "percentage": false, + "pluginVersion": "8.4.3", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, + "expr": "sum(rate(synapse_push_bulk_push_rule_evaluator_push_rules_state_size_counter{job=\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size]))", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{index}}", + "metric": "synapse_push_bulk_push_rule_evaluator_push_rules_state_size_counter", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeRegions": [], + "title": "Iterations over State", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "hertz", + "label": "", + "logBase": 1, + "min": "0", + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": true + } + ], + "yaxis": { + "align": false + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "Rate that the cached push rules for a room get invalidated due to underlying push rules being changed. ", + "fieldConfig": { + "defaults": { + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 33 + }, + "hiddenSeries": false, + "id": 211, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "alertThreshold": true + }, + "paceLength": 10, + "percentage": false, + "pluginVersion": "8.4.3", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "exemplar": true, + "expr": "sum(rate(synapse_push_bulk_push_rule_evaluator_push_rules_invalidation_counter{job=\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size]))", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{index}}", + "metric": "synapse_push_bulk_push_rule_evaluator_push_rules_invalidation_counter", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeRegions": [], + "title": "Push Rule Invalidations", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "hertz", + "label": "", + "logBase": 1, + "min": "0", + "show": true + }, + { + "format": "short", + "logBase": 1, + "show": true + } + ], + "yaxis": { + "align": false + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "How often the \"delta optimisation\" happens.\n\nThe delta optimisation is when we update the push rules for a room incrementally after a state change where we know the delta between the old state and the new state.\n\nThis can't happen if we don't the delta or we're calculating push rules from scratch.", + "fieldConfig": { + "defaults": { + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 40 + }, + "hiddenSeries": false, + "id": 213, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "alertThreshold": true + }, + "paceLength": 10, + "percentage": false, + "pluginVersion": "8.4.3", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "Number of calls", + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, + "expr": "sum(rate(synapse_util_caches_cache:hits{job=\"$job\",index=~\"$index\",name=\"push_rules_delta_state_cache_metric\",instance=\"$instance\"}[$bucket_size]))/sum(rate(synapse_util_caches_cache:total{job=\"$job\",index=~\"$index\", name=\"push_rules_delta_state_cache_metric\",instance=\"$instance\"}[$bucket_size]))", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Hit Rate", + "metric": "synapse_push_bulk_push_rule_evaluator_push_rules_invalidation_counter", + "refId": "A", + "step": 2 + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, + "expr": "sum(rate(synapse_util_caches_cache:total{job=\"$job\",index=~\"$index\", name=\"push_rules_delta_state_cache_metric\",instance=\"$instance\"}[$bucket_size]))", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Number of calls", + "refId": "B", + "step": 2 + } + ], + "thresholds": [], + "timeRegions": [], + "title": "Delta Optimisation", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percentunit", + "label": "", + "logBase": 1, + "max": "1", + "min": "0", + "show": true + }, + { + "format": "hertz", + "label": "", + "logBase": 1, + "min": "0", + "show": true + } + ], + "yaxis": { + "align": false + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "How often we have the correct cached push rules for a room.", + "fieldConfig": { + "defaults": { + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 40 + }, + "hiddenSeries": false, + "id": 215, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "alertThreshold": true + }, + "paceLength": 10, + "percentage": false, + "pluginVersion": "8.4.3", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "Number of calls", + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, + "expr": "sum(rate(synapse_util_caches_cache:hits{job=\"$job\",index=~\"$index\",name=\"room_push_rule_cache\",instance=\"$instance\"}[$bucket_size]))/sum(rate(synapse_util_caches_cache:total{job=\"$job\",index=~\"$index\", name=\"room_push_rule_cache\",instance=\"$instance\"}[$bucket_size]))", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Hit Rate", + "metric": "synapse_push_bulk_push_rule_evaluator_push_rules_invalidation_counter", + "refId": "A", + "step": 2 + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, + "expr": "sum(rate(synapse_util_caches_cache:total{job=\"$job\",index=~\"$index\", name=\"room_push_rule_cache\",instance=\"$instance\"}[$bucket_size]))", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Number of calls", + "refId": "B", + "step": 2 + } + ], + "thresholds": [], + "timeRegions": [], + "title": "How often we reuse existing calculated push rules", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percentunit", + "label": "", + "logBase": 1, + "max": "1", + "min": "0", + "show": true + }, + { + "format": "hertz", + "logBase": 1, + "show": true + } + ], + "yaxis": { + "align": false + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "How often we have existing cached push rules for the room. \n\nNote that these might be outdated and need to be recalculated if the state has changed.", + "fieldConfig": { + "defaults": { + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 47 + }, + "hiddenSeries": false, + "id": 217, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "alertThreshold": true + }, + "paceLength": 10, + "percentage": false, + "pluginVersion": "8.4.3", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "Number of calls", + "yaxis": 2 + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, + "expr": "sum(rate(synapse_util_caches_cache:hits{job=\"$job\",index=~\"$index\",name=\"_get_rules_for_room\",instance=\"$instance\"}[$bucket_size]))/sum(rate(synapse_util_caches_cache:total{job=\"$job\",index=~\"$index\", name=\"_get_rules_for_room\",instance=\"$instance\"}[$bucket_size]))", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Hit Rate", + "metric": "synapse_push_bulk_push_rule_evaluator_push_rules_invalidation_counter", + "refId": "A", + "step": 2 + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, + "expr": "sum(rate(synapse_util_caches_cache:total{job=\"$job\",index=~\"$index\", name=\"_get_rules_for_room\",instance=\"$instance\"}[$bucket_size]))", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Number of calls", + "refId": "B", + "step": 2 + } + ], + "thresholds": [], + "timeRegions": [], + "title": "How often we have the RulesForRoom cached", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "mode": "time", + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percentunit", + "label": "", + "logBase": 1, + "max": "1", + "min": "0", + "show": true + }, + { + "format": "hertz", + "logBase": 1, + "show": true + } + ], + "yaxis": { + "align": false + } + } + ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" + } + ], + "title": "Push Rule Cache", + "type": "row" + }, + { + "collapsed": true, + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 33 + }, + "id": 58, + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": { + "uid": "$datasource" + }, + "fieldConfig": { + "defaults": { + "links": [] + }, + "overrides": [] + }, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 9 + }, + "hiddenSeries": false, "id": 48, "legend": { "avg": false, @@ -4984,7 +5747,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -4994,6 +5757,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_storage_schedule_time_sum{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])/rate(synapse_storage_schedule_time_count[$bucket_size])", "format": "time_series", "intervalFactor": 2, @@ -5003,9 +5769,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Avg time waiting for db conn", "tooltip": { "shared": true, @@ -5014,34 +5778,26 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "decimals": null, "format": "s", "label": "", "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": false } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -5049,11 +5805,12 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "Shows the time in which the given percentage of database queries were scheduled, over the sampled timespan", "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -5064,7 +5821,7 @@ "h": 7, "w": 12, "x": 12, - "y": 33 + "y": 9 }, "hiddenSeries": false, "id": 104, @@ -5087,7 +5844,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -5097,6 +5854,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.99, rate(synapse_storage_schedule_time_bucket{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]))", "format": "time_series", "hide": false, @@ -5106,6 +5866,9 @@ "step": 20 }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.95, rate(synapse_storage_schedule_time_bucket{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]))", "format": "time_series", "intervalFactor": 1, @@ -5113,6 +5876,9 @@ "refId": "B" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.90, rate(synapse_storage_schedule_time_bucket{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]))", "format": "time_series", "intervalFactor": 1, @@ -5120,6 +5886,9 @@ "refId": "C" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_storage_schedule_time_sum{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])/rate(synapse_storage_schedule_time_count{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "interval": "", @@ -5129,9 +5898,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Db scheduling time quantiles", "tooltip": { "shared": false, @@ -5140,34 +5907,26 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "decimals": null, "format": "s", "label": "", "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": false } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -5175,12 +5934,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -5192,7 +5952,7 @@ "h": 7, "w": 12, "x": 0, - "y": 40 + "y": 16 }, "hiddenSeries": false, "id": 10, @@ -5216,7 +5976,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -5226,6 +5986,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "topk(10, rate(synapse_storage_transaction_time_count{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]))", "format": "time_series", "interval": "", @@ -5236,9 +5999,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Top DB transactions by txn rate", "tooltip": { "shared": false, @@ -5247,9 +6008,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -5257,21 +6016,17 @@ { "format": "hertz", "logBase": 1, - "max": null, "min": 0, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -5279,12 +6034,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -5296,7 +6052,7 @@ "h": 7, "w": 12, "x": 12, - "y": 40 + "y": 16 }, "hiddenSeries": false, "id": 11, @@ -5320,7 +6076,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -5330,6 +6086,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_storage_transaction_time_sum{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "instant": false, @@ -5341,9 +6100,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "DB transactions by total txn time", "tooltip": { "shared": false, @@ -5352,9 +6109,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -5362,21 +6117,16 @@ { "format": "percentunit", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -5384,12 +6134,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -5401,7 +6152,7 @@ "h": 7, "w": 12, "x": 0, - "y": 47 + "y": 23 }, "hiddenSeries": false, "id": 180, @@ -5425,7 +6176,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -5435,6 +6186,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_storage_transaction_time_sum{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])/rate(synapse_storage_transaction_time_count{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "instant": false, @@ -5446,9 +6200,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Average DB txn time", "tooltip": { "shared": false, @@ -5457,9 +6209,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -5467,21 +6217,16 @@ { "format": "s", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -5489,10 +6234,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -5503,7 +6249,7 @@ "h": 9, "w": 12, "x": 12, - "y": 47 + "y": 23 }, "hiddenSeries": false, "id": 200, @@ -5524,7 +6270,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -5534,6 +6280,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.99, sum(rate(synapse_storage_schedule_time_bucket{index=~\"$index\",instance=\"$instance\",job=\"$job\"}[$bucket_size])) by (le))", "format": "time_series", "intervalFactor": 1, @@ -5541,6 +6290,9 @@ "refId": "D" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.9, sum(rate(synapse_storage_schedule_time_bucket{index=~\"$index\",instance=\"$instance\",job=\"$job\"}[$bucket_size])) by (le))", "format": "time_series", "intervalFactor": 1, @@ -5548,6 +6300,9 @@ "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.75, sum(rate(synapse_storage_schedule_time_bucket{index=~\"$index\",instance=\"$instance\",job=\"$job\"}[$bucket_size])) by (le))", "format": "time_series", "intervalFactor": 1, @@ -5555,6 +6310,9 @@ "refId": "C" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.5, sum(rate(synapse_storage_schedule_time_bucket{index=~\"$index\",instance=\"$instance\",job=\"$job\"}[$bucket_size])) by (le))", "format": "time_series", "intervalFactor": 1, @@ -5563,9 +6321,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Time waiting for DB connection quantiles", "tooltip": { "shared": true, @@ -5574,49 +6330,54 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "decimals": null, + "$$hashKey": "object:203", "format": "s", "label": "", "logBase": 1, - "max": null, "min": "0", "show": true }, { + "$$hashKey": "object:204", "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": false } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], - "repeat": null, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" + } + ], "title": "Database", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 33 + "y": 34 }, "id": 59, "panels": [ @@ -5625,12 +6386,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -5642,7 +6404,7 @@ "h": 13, "w": 12, "x": 0, - "y": 9 + "y": 10 }, "hiddenSeries": false, "id": 12, @@ -5660,9 +6422,12 @@ "linewidth": 2, "links": [], "nullPointMode": "null", + "options": { + "alertThreshold": true + }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.1.3", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -5672,6 +6437,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_util_metrics_block_ru_utime_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\",block_name!=\"wrapped_request_handler\"}[$bucket_size]) + rate(synapse_util_metrics_block_ru_stime_seconds[$bucket_size])", "format": "time_series", "interval": "", @@ -5682,9 +6450,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Total CPU Usage by Block", "tooltip": { "shared": true, @@ -5693,9 +6459,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -5703,21 +6467,16 @@ { "format": "percentunit", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -5725,12 +6484,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -5742,7 +6502,7 @@ "h": 13, "w": 12, "x": 12, - "y": 9 + "y": 10 }, "hiddenSeries": false, "id": 26, @@ -5760,9 +6520,12 @@ "linewidth": 2, "links": [], "nullPointMode": "null", + "options": { + "alertThreshold": true + }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.1.3", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -5772,6 +6535,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "(rate(synapse_util_metrics_block_ru_utime_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]) + rate(synapse_util_metrics_block_ru_stime_seconds[$bucket_size])) / rate(synapse_util_metrics_block_count[$bucket_size])", "format": "time_series", "interval": "", @@ -5782,9 +6548,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Average CPU Time per Block", "tooltip": { "shared": true, @@ -5793,9 +6557,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -5803,21 +6565,16 @@ { "format": "ms", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -5825,12 +6582,14 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -5842,7 +6601,7 @@ "h": 13, "w": 12, "x": 0, - "y": 22 + "y": 23 }, "hiddenSeries": false, "id": 13, @@ -5860,9 +6619,12 @@ "linewidth": 2, "links": [], "nullPointMode": "null", + "options": { + "alertThreshold": true + }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.1.3", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -5872,19 +6634,22 @@ "steppedLine": false, "targets": [ { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, "expr": "rate(synapse_util_metrics_block_db_txn_duration_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "interval": "", "intervalFactor": 2, - "legendFormat": "{{job}} {{block_name}}", + "legendFormat": "{{job}}-{{index}} {{block_name}}", "refId": "A", "step": 20 } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Total DB Usage by Block", "tooltip": { "shared": true, @@ -5893,31 +6658,27 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { + "$$hashKey": "object:196", "format": "percentunit", "logBase": 1, - "max": null, "min": 0, "show": true }, { + "$$hashKey": "object:197", "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -5925,13 +6686,14 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "The time each database transaction takes to execute, on average, broken down by metrics block.", "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -5943,7 +6705,7 @@ "h": 13, "w": 12, "x": 12, - "y": 22 + "y": 23 }, "hiddenSeries": false, "id": 27, @@ -5961,9 +6723,12 @@ "linewidth": 2, "links": [], "nullPointMode": "null", + "options": { + "alertThreshold": true + }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.1.3", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -5973,6 +6738,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_util_metrics_block_db_txn_duration_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]) / rate(synapse_util_metrics_block_db_txn_count{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "interval": "", @@ -5983,9 +6751,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Average Database Transaction time, by Block", "tooltip": { "shared": true, @@ -5994,9 +6760,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -6004,21 +6768,16 @@ { "format": "ms", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -6026,12 +6785,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -6043,7 +6803,7 @@ "h": 13, "w": 12, "x": 0, - "y": 35 + "y": 36 }, "hiddenSeries": false, "id": 28, @@ -6060,9 +6820,12 @@ "linewidth": 2, "links": [], "nullPointMode": "null", + "options": { + "alertThreshold": true + }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.1.3", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -6072,6 +6835,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_util_metrics_block_db_txn_duration_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]) / rate(synapse_util_metrics_block_db_txn_count{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "interval": "", @@ -6082,9 +6848,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Average Transactions per Block", "tooltip": { "shared": false, @@ -6093,9 +6857,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -6103,21 +6865,16 @@ { "format": "none", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -6125,12 +6882,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -6142,7 +6900,7 @@ "h": 13, "w": 12, "x": 12, - "y": 35 + "y": 36 }, "hiddenSeries": false, "id": 25, @@ -6159,9 +6917,12 @@ "linewidth": 2, "links": [], "nullPointMode": "null", + "options": { + "alertThreshold": true + }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.1.3", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -6171,6 +6932,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_util_metrics_block_time_seconds{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]) / rate(synapse_util_metrics_block_count[$bucket_size])", "format": "time_series", "interval": "", @@ -6181,9 +6945,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Average Wallclock Time per Block", "tooltip": { "shared": false, @@ -6192,9 +6954,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -6202,21 +6962,16 @@ { "format": "ms", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -6224,12 +6979,8 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", - "fieldConfig": { - "defaults": { - "custom": {} - }, - "overrides": [] + "datasource": { + "uid": "$datasource" }, "fill": 1, "fillGradient": 0, @@ -6237,7 +6988,7 @@ "h": 15, "w": 12, "x": 0, - "y": 48 + "y": 49 }, "hiddenSeries": false, "id": 154, @@ -6254,8 +7005,11 @@ "lines": true, "linewidth": 1, "nullPointMode": "null", + "options": { + "alertThreshold": true + }, "percentage": false, - "pluginVersion": "7.1.3", + "pluginVersion": "8.4.3", "pointradius": 2, "points": false, "renderer": "flot", @@ -6265,6 +7019,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_util_metrics_block_count{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "interval": "", "legendFormat": "{{job}}-{{index}} {{block_name}}", @@ -6272,9 +7029,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Block count", "tooltip": { "shared": true, @@ -6283,48 +7038,50 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], - "repeat": null, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" + } + ], "title": "Per-block metrics", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 34 + "y": 35 }, "id": 61, "panels": [ @@ -6333,13 +7090,14 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "decimals": 2, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -6351,7 +7109,7 @@ "h": 10, "w": 12, "x": 0, - "y": 35 + "y": 36 }, "hiddenSeries": false, "id": 1, @@ -6375,7 +7133,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -6385,6 +7143,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_util_caches_cache:hits{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])/rate(synapse_util_caches_cache:total{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "format": "time_series", "intervalFactor": 2, @@ -6394,9 +7155,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Cache Hit Ratio", "tooltip": { "msResolution": true, @@ -6406,15 +7165,12 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "decimals": null, "format": "percentunit", "label": "", "logBase": 1, @@ -6425,14 +7181,11 @@ { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": false } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -6440,12 +7193,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -6457,7 +7211,7 @@ "h": 10, "w": 12, "x": 12, - "y": 35 + "y": 36 }, "hiddenSeries": false, "id": 8, @@ -6480,7 +7234,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -6490,6 +7244,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_util_caches_cache:size{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "format": "time_series", "hide": false, @@ -6501,9 +7258,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Cache Size", "tooltip": { "shared": false, @@ -6512,9 +7267,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -6522,21 +7275,17 @@ { "format": "short", "logBase": 1, - "max": null, "min": 0, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -6544,12 +7293,13 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "editable": true, "error": false, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -6561,7 +7311,7 @@ "h": 10, "w": 12, "x": 0, - "y": 45 + "y": 46 }, "hiddenSeries": false, "id": 38, @@ -6584,7 +7334,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -6594,6 +7344,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_util_caches_cache:total{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "format": "time_series", "interval": "", @@ -6604,9 +7357,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Cache request rate", "tooltip": { "shared": false, @@ -6615,9 +7366,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -6625,21 +7374,17 @@ { "format": "rps", "logBase": 1, - "max": null, "min": 0, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -6647,10 +7392,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -6661,7 +7407,7 @@ "h": 10, "w": 12, "x": 12, - "y": 45 + "y": 46 }, "hiddenSeries": false, "id": 39, @@ -6683,7 +7429,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -6693,6 +7439,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "topk(10, rate(synapse_util_caches_cache:total{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size]) - rate(synapse_util_caches_cache:hits{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size]))", "format": "time_series", "interval": "", @@ -6703,9 +7452,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Top 10 cache misses", "tooltip": { "shared": false, @@ -6714,33 +7461,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "rps", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -6748,10 +7486,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -6762,7 +7501,7 @@ "h": 9, "w": 12, "x": 0, - "y": 55 + "y": 56 }, "hiddenSeries": false, "id": 65, @@ -6784,7 +7523,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 5, "points": false, "renderer": "flot", @@ -6794,17 +7533,19 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_util_caches_cache:evicted_size{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", + "interval": "", "intervalFactor": 1, "legendFormat": "{{name}} ({{reason}}) {{job}}-{{index}}", "refId": "A" } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Cache eviction rate", "tooltip": { "shared": false, @@ -6813,49 +7554,51 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "decimals": null, "format": "hertz", "label": "entries / second", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], - "repeat": null, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" + } + ], "title": "Caches", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 35 + "y": 36 }, "id": 148, "panels": [ @@ -6864,7 +7607,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {}, @@ -6908,6 +7653,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_util_caches_response_cache:size{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "interval": "", "legendFormat": "{{name}} {{job}}-{{index}}", @@ -6915,9 +7663,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Response cache size", "tooltip": { "shared": false, @@ -6926,33 +7672,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -6960,7 +7697,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {}, @@ -7004,12 +7743,18 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_util_caches_response_cache:hits{instance=\"$instance\", job=~\"$job\", index=~\"$index\"}[$bucket_size])/rate(synapse_util_caches_response_cache:total{instance=\"$instance\", job=~\"$job\", index=~\"$index\"}[$bucket_size])", "interval": "", "legendFormat": "{{name}} {{job}}-{{index}}", "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "", "interval": "", "legendFormat": "", @@ -7017,9 +7762,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Response cache hit rate", "tooltip": { "shared": false, @@ -7028,17 +7771,13 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "decimals": null, "format": "percentunit", - "label": null, "logBase": 1, "max": "1", "min": "0", @@ -7046,30 +7785,38 @@ }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" + } + ], "title": "Response caches", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 36 + "y": 37 }, "id": 62, "panels": [ @@ -7078,7 +7825,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {}, @@ -7123,6 +7872,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(python_gc_time_sum{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[10m])", "format": "time_series", "instant": false, @@ -7132,9 +7884,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Total GC time by bucket (10m smoothing)", "tooltip": { "shared": true, @@ -7143,34 +7893,25 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "decimals": null, "format": "percentunit", - "label": null, "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -7178,7 +7919,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "decimals": 3, "editable": true, "error": false, @@ -7228,6 +7971,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(python_gc_time_sum{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])/rate(python_gc_time_count[$bucket_size])", "format": "time_series", "intervalFactor": 2, @@ -7238,9 +7984,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Average GC Time Per Collection", "tooltip": { "shared": false, @@ -7249,9 +7993,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -7259,21 +8001,16 @@ { "format": "s", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -7281,7 +8018,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "'gen 0' shows the number of objects allocated since the last gen0 GC.\n'gen 1' / 'gen 2' show the number of gen0/gen1 GCs since the last gen1/gen2 GC.", "fieldConfig": { "defaults": { @@ -7334,6 +8073,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "python_gc_counts{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}", "format": "time_series", "intervalFactor": 1, @@ -7342,9 +8084,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Allocation counts", "tooltip": { "shared": false, @@ -7353,9 +8093,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -7364,23 +8102,17 @@ "format": "short", "label": "Gen N-1 GCs since last Gen N GC", "logBase": 1, - "max": null, - "min": null, "show": true }, { - "decimals": null, "format": "short", "label": "Objects since last Gen 0 GC", "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -7388,7 +8120,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {}, @@ -7433,6 +8167,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(python_gc_unreachable_total{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])/rate(python_gc_time_count{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "intervalFactor": 1, @@ -7441,9 +8178,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Object counts per collection", "tooltip": { "shared": true, @@ -7452,33 +8187,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -7486,7 +8212,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {}, @@ -7531,6 +8259,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(python_gc_time_count{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "time_series", "intervalFactor": 1, @@ -7539,9 +8270,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "GC frequency", "tooltip": { "shared": true, @@ -7550,51 +8279,43 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { "cards": { - "cardPadding": 0, - "cardRound": null + "cardPadding": 0 }, "color": { "cardColor": "#b4ff00", "colorScale": "sqrt", "colorScheme": "interpolateSpectral", "exponent": 0.5, - "max": null, "min": 0, "mode": "spectrum" }, "dataFormat": "tsbuckets", - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, "fieldConfig": { "defaults": { "custom": {} @@ -7618,6 +8339,10 @@ "reverseYBuckets": false, "targets": [ { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, "expr": "sum(rate(python_gc_time_bucket[$bucket_size])) by (le)", "format": "heatmap", "intervalFactor": 1, @@ -7634,34 +8359,37 @@ "xAxis": { "show": true }, - "xBucketNumber": null, - "xBucketSize": null, "yAxis": { - "decimals": null, "format": "s", "logBase": 1, - "max": null, - "min": null, - "show": true, - "splitFactor": null + "show": true }, - "yBucketBound": "auto", - "yBucketNumber": null, - "yBucketSize": null + "yBucketBound": "auto" + } + ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" } ], - "repeat": null, "title": "GC", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 37 + "y": 38 }, "id": 63, "panels": [ @@ -7670,10 +8398,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -7684,10 +8413,10 @@ "h": 7, "w": 12, "x": 0, - "y": 13 + "y": 14 }, "hiddenSeries": false, - "id": 42, + "id": 43, "legend": { "avg": false, "current": false, @@ -7706,7 +8435,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.4.3", "pointradius": 5, "points": false, "renderer": "flot", @@ -7716,7 +8445,10 @@ "steppedLine": false, "targets": [ { - "expr": "sum (rate(synapse_replication_tcp_protocol_inbound_commands{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])) without (name, conn_id)", + "datasource": { + "uid": "$datasource" + }, + "expr": "sum (rate(synapse_replication_tcp_protocol_outbound_commands{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])) without (name, conn_id)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{job}}-{{index}} {{command}}", @@ -7725,10 +8457,8 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, - "title": "Rate of incoming commands", + "title": "Rate of outgoing commands", "tooltip": { "shared": false, "sort": 0, @@ -7736,241 +8466,326 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "${DS_PROMETHEUS}", - "description": "", + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, - "links": [] + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "hertz" }, "overrides": [] }, - "fill": 1, - "fillGradient": 0, "gridPos": { "h": 7, "w": 12, "x": 12, - "y": 13 - }, - "hiddenSeries": false, - "id": 144, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false + "y": 14 }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", + "id": 41, + "links": [], "options": { - "alertThreshold": true + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom" + }, + "tooltip": { + "mode": "single", + "sort": "none" + } }, - "percentage": false, - "pluginVersion": "7.3.7", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, + "pluginVersion": "8.4.3", "targets": [ { - "expr": "synapse_replication_tcp_command_queue{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, + "expr": "rate(synapse_replication_tcp_resource_stream_updates{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", + "format": "time_series", "interval": "", - "legendFormat": "{{stream_name}} {{job}}-{{index}}", - "refId": "A" - } - ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Queued incoming RDATA commands, by stream", - "tooltip": { - "shared": false, - "sort": 0, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true + "intervalFactor": 2, + "legendFormat": "{{stream_name}}", + "refId": "A", + "step": 20 } ], - "yaxis": { - "align": false, - "alignLevel": null - } + "title": "Rate of outgoing RDATA commands, by stream", + "type": "timeseries" }, { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "$datasource", + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, - "links": [] + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "hertz" }, "overrides": [] }, - "fill": 1, - "fillGradient": 0, "gridPos": { "h": 7, "w": 12, "x": 0, - "y": 20 - }, - "hiddenSeries": false, - "id": 43, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false + "y": 21 }, - "lines": true, - "linewidth": 1, + "id": 42, "links": [], - "nullPointMode": "null", "options": { - "alertThreshold": true + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom" + }, + "tooltip": { + "mode": "single", + "sort": "none" + } }, - "paceLength": 10, - "percentage": false, - "pluginVersion": "7.3.7", - "pointradius": 5, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, + "pluginVersion": "8.4.3", "targets": [ { - "expr": "sum (rate(synapse_replication_tcp_protocol_outbound_commands{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])) without (name, conn_id)", + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, + "expr": "sum (rate(synapse_replication_tcp_protocol_inbound_commands{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])) without (name, conn_id)", "format": "time_series", + "interval": "", "intervalFactor": 2, "legendFormat": "{{job}}-{{index}} {{command}}", "refId": "A", "step": 20 } ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, - "title": "Rate of outgoing commands", - "tooltip": { - "shared": false, - "sort": 0, - "value_type": "individual" + "title": "Rate of incoming commands (including echoes)", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 1, + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "hertz" + }, + "overrides": [] }, - "yaxes": [ - { - "format": "hertz", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 21 + }, + "id": 220, + "links": [], + "options": { + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom" }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "pluginVersion": "8.4.3", + "targets": [ { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "exemplar": true, + "expr": "rate(synapse_replication_tcp_protocol_inbound_rdata_count{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{job}}-{{index}} {{stream_name}}", + "refId": "A", + "step": 20 } ], - "yaxis": { - "align": false, - "alignLevel": null - } + "title": "Rate of incoming RDATA commands (excluding echoes), by stream", + "type": "timeseries" }, { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "", "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -7980,11 +8795,11 @@ "gridPos": { "h": 7, "w": 12, - "x": 12, - "y": 20 + "x": 0, + "y": 28 }, "hiddenSeries": false, - "id": 41, + "id": 144, "legend": { "avg": false, "current": false, @@ -7996,15 +8811,13 @@ }, "lines": true, "linewidth": 1, - "links": [], "nullPointMode": "null", "options": { "alertThreshold": true }, - "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", - "pointradius": 5, + "pluginVersion": "8.4.3", + "pointradius": 2, "points": false, "renderer": "flot", "seriesOverrides": [], @@ -8013,20 +8826,19 @@ "steppedLine": false, "targets": [ { - "expr": "rate(synapse_replication_tcp_resource_stream_updates{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", - "format": "time_series", + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "synapse_replication_tcp_command_queue{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "interval": "", - "intervalFactor": 2, - "legendFormat": "{{stream_name}}", - "refId": "A", - "step": 20 + "legendFormat": "{{stream_name}} {{job}}-{{index}}", + "refId": "A" } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, - "title": "Outgoing stream updates", + "title": "Queued incoming RDATA commands, by stream", "tooltip": { "shared": false, "sort": 0, @@ -8034,33 +8846,26 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "format": "hertz", - "label": null, + "$$hashKey": "object:218", + "format": "short", "logBase": 1, - "max": null, - "min": null, "show": true }, { + "$$hashKey": "object:219", "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -8068,10 +8873,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -8081,11 +8887,11 @@ "gridPos": { "h": 7, "w": 12, - "x": 0, - "y": 27 + "x": 12, + "y": 28 }, "hiddenSeries": false, - "id": 113, + "id": 115, "legend": { "avg": false, "current": false, @@ -8104,7 +8910,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.4.3", "pointradius": 5, "points": false, "renderer": "flot", @@ -8114,25 +8920,19 @@ "steppedLine": false, "targets": [ { - "expr": "synapse_replication_tcp_resource_connections_per_stream{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}", + "datasource": { + "uid": "$datasource" + }, + "expr": "rate(synapse_replication_tcp_protocol_close_reason{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "format": "time_series", "intervalFactor": 1, - "legendFormat": "{{job}}-{{index}} {{stream_name}}", + "legendFormat": "{{job}}-{{index}} {{reason_type}}", "refId": "A" - }, - { - "expr": "synapse_replication_tcp_resource_total_connections{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}", - "format": "time_series", - "intervalFactor": 1, - "legendFormat": "{{job}}-{{index}}", - "refId": "B" } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, - "title": "Replication connections", + "title": "Replication connection close reasons", "tooltip": { "shared": true, "sort": 0, @@ -8140,33 +8940,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "format": "short", - "label": null, + "format": "hertz", "logBase": 1, - "max": null, - "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -8174,10 +8965,11 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {}, "links": [] }, "overrides": [] @@ -8187,11 +8979,11 @@ "gridPos": { "h": 7, "w": 12, - "x": 12, - "y": 27 + "x": 0, + "y": 35 }, "hiddenSeries": false, - "id": 115, + "id": 113, "legend": { "avg": false, "current": false, @@ -8210,7 +9002,7 @@ }, "paceLength": 10, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.4.3", "pointradius": 5, "points": false, "renderer": "flot", @@ -8220,18 +9012,29 @@ "steppedLine": false, "targets": [ { - "expr": "rate(synapse_replication_tcp_protocol_close_reason{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", + "datasource": { + "uid": "$datasource" + }, + "expr": "synapse_replication_tcp_resource_connections_per_stream{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}", "format": "time_series", "intervalFactor": 1, - "legendFormat": "{{job}}-{{index}} {{reason_type}}", + "legendFormat": "{{job}}-{{index}} {{stream_name}}", "refId": "A" + }, + { + "datasource": { + "uid": "$datasource" + }, + "expr": "synapse_replication_tcp_resource_total_connections{job=~\"$job\",index=~\"$index\",instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{job}}-{{index}}", + "refId": "B" } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, - "title": "Replication connection close reasons", + "title": "Replication connections", "tooltip": { "shared": true, "sort": 0, @@ -8239,48 +9042,51 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "format": "hertz", - "label": null, + "format": "short", "logBase": 1, - "max": null, - "min": null, + "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], - "repeat": null, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" + } + ], "title": "Replication", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 38 + "y": 39 }, "id": 69, "panels": [ @@ -8289,7 +9095,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {}, @@ -8335,6 +9143,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "max(synapse_event_persisted_position{instance=\"$instance\"}) - on() group_right() synapse_event_processing_positions{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "format": "time_series", "interval": "", @@ -8344,9 +9155,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Event processing lag", "tooltip": { "shared": true, @@ -8355,9 +9164,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -8366,22 +9173,17 @@ "format": "short", "label": "events", "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -8389,7 +9191,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {}, @@ -8435,6 +9239,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "time()*1000-synapse_event_processing_last_ts{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}", "format": "time_series", "hide": false, @@ -8445,9 +9252,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Age of last processed event", "tooltip": { "shared": true, @@ -8456,33 +9261,25 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "ms", - "label": null, "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -8490,7 +9287,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {}, @@ -8537,6 +9336,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "deriv(synapse_event_processing_last_ts{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])/1000 - 1", "format": "time_series", "hide": false, @@ -8547,9 +9349,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Event processing catchup rate", "tooltip": { "shared": true, @@ -8558,67 +9358,70 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "decimals": null, "format": "none", "label": "fallbehind(-) / catchup(+): s/sec", "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" + } + ], "title": "Event processing loop positions", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 39 + "y": 40 }, "id": 126, "panels": [ { "cards": { - "cardPadding": 0, - "cardRound": null + "cardPadding": 0 }, "color": { "cardColor": "#B877D9", "colorScale": "sqrt", "colorScheme": "interpolateInferno", "exponent": 0.5, - "max": null, "min": 0, "mode": "opacity" }, "dataFormat": "tsbuckets", - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "Colour reflects the number of rooms with the given number of forward extremities, or fewer.\n\nThis is only updated once an hour.", "fieldConfig": { "defaults": { @@ -8643,6 +9446,9 @@ "reverseYBuckets": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_forward_extremities_bucket{instance=\"$instance\"} and on (index, instance, job) (synapse_storage_events_persisted_events > 0)", "format": "heatmap", "intervalFactor": 1, @@ -8650,8 +9456,6 @@ "refId": "A" } ], - "timeFrom": null, - "timeShift": null, "title": "Number of rooms, by number of forward extremities in room", "tooltip": { "show": true, @@ -8661,27 +9465,22 @@ "xAxis": { "show": true }, - "xBucketNumber": null, - "xBucketSize": null, "yAxis": { "decimals": 0, "format": "short", "logBase": 1, - "max": null, - "min": null, - "show": true, - "splitFactor": null + "show": true }, - "yBucketBound": "auto", - "yBucketNumber": null, - "yBucketSize": null + "yBucketBound": "auto" }, { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "Number of rooms with the given number of forward extremities or fewer.\n\nThis is only updated once an hour.", "fieldConfig": { "defaults": { @@ -8725,6 +9524,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_forward_extremities_bucket{instance=\"$instance\"} > 0", "format": "heatmap", "interval": "", @@ -8734,9 +9536,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Room counts, by number of extremities", "tooltip": { "shared": true, @@ -8745,40 +9545,30 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { - "decimals": null, "format": "none", "label": "Number of rooms", "logBase": 10, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": false } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { "cards": { - "cardPadding": 0, - "cardRound": null + "cardPadding": 0 }, "color": { "cardColor": "#5794F2", @@ -8789,7 +9579,9 @@ "mode": "opacity" }, "dataFormat": "tsbuckets", - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "Colour reflects the number of events persisted to rooms with the given number of forward extremities, or fewer.", "fieldConfig": { "defaults": { @@ -8814,6 +9606,9 @@ "reverseYBuckets": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_storage_events_forward_extremities_persisted_bucket{instance=\"$instance\"}[$bucket_size]) and on (index, instance, job) (synapse_storage_events_persisted_events > 0)", "format": "heatmap", "intervalFactor": 1, @@ -8821,8 +9616,6 @@ "refId": "A" } ], - "timeFrom": null, - "timeShift": null, "title": "Events persisted, by number of forward extremities in room (heatmap)", "tooltip": { "show": true, @@ -8832,27 +9625,22 @@ "xAxis": { "show": true }, - "xBucketNumber": null, - "xBucketSize": null, "yAxis": { "decimals": 0, "format": "short", "logBase": 1, - "max": null, - "min": null, - "show": true, - "splitFactor": null + "show": true }, - "yBucketBound": "auto", - "yBucketNumber": null, - "yBucketSize": null + "yBucketBound": "auto" }, { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "For a given percentage P, the number X where P% of events were persisted to rooms with X forward extremities or fewer.", "fieldConfig": { "defaults": { @@ -8895,6 +9683,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.5, rate(synapse_storage_events_forward_extremities_persisted_bucket{instance=\"$instance\"}[$bucket_size]) and on (index, instance, job) (synapse_storage_events_persisted_events > 0))", "format": "time_series", "intervalFactor": 1, @@ -8902,6 +9693,9 @@ "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.75, rate(synapse_storage_events_forward_extremities_persisted_bucket{instance=\"$instance\"}[$bucket_size]) and on (index, instance, job) (synapse_storage_events_persisted_events > 0))", "format": "time_series", "intervalFactor": 1, @@ -8909,6 +9703,9 @@ "refId": "B" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.90, rate(synapse_storage_events_forward_extremities_persisted_bucket{instance=\"$instance\"}[$bucket_size]) and on (index, instance, job) (synapse_storage_events_persisted_events > 0))", "format": "time_series", "intervalFactor": 1, @@ -8916,6 +9713,9 @@ "refId": "C" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.99, rate(synapse_storage_events_forward_extremities_persisted_bucket{instance=\"$instance\"}[$bucket_size]) and on (index, instance, job) (synapse_storage_events_persisted_events > 0))", "format": "time_series", "intervalFactor": 1, @@ -8924,9 +9724,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Events persisted, by number of forward extremities in room (quantiles)", "tooltip": { "shared": true, @@ -8935,9 +9733,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -8946,28 +9742,22 @@ "format": "short", "label": "Number of extremities in room", "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { "cards": { - "cardPadding": 0, - "cardRound": null + "cardPadding": 0 }, "color": { "cardColor": "#FF9830", @@ -8978,7 +9768,9 @@ "mode": "opacity" }, "dataFormat": "tsbuckets", - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "Colour reflects the number of events persisted to rooms with the given number of stale forward extremities, or fewer.\n\nStale forward extremities are those that were in the previous set of extremities as well as the new.", "fieldConfig": { "defaults": { @@ -9003,6 +9795,9 @@ "reverseYBuckets": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_storage_events_stale_forward_extremities_persisted_bucket{instance=\"$instance\"}[$bucket_size]) and on (index, instance, job) (synapse_storage_events_persisted_events > 0)", "format": "heatmap", "intervalFactor": 1, @@ -9010,8 +9805,6 @@ "refId": "A" } ], - "timeFrom": null, - "timeShift": null, "title": "Events persisted, by number of stale forward extremities in room (heatmap)", "tooltip": { "show": true, @@ -9021,27 +9814,22 @@ "xAxis": { "show": true }, - "xBucketNumber": null, - "xBucketSize": null, "yAxis": { "decimals": 0, "format": "short", "logBase": 1, - "max": null, - "min": null, - "show": true, - "splitFactor": null + "show": true }, - "yBucketBound": "auto", - "yBucketNumber": null, - "yBucketSize": null + "yBucketBound": "auto" }, { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "For given percentage P, the number X where P% of events were persisted to rooms with X stale forward extremities or fewer.\n\nStale forward extremities are those that were in the previous set of extremities as well as the new.", "fieldConfig": { "defaults": { @@ -9084,6 +9872,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.5, rate(synapse_storage_events_stale_forward_extremities_persisted_bucket{instance=\"$instance\"}[$bucket_size]) and on (index, instance, job) (synapse_storage_events_persisted_events > 0))", "format": "time_series", "intervalFactor": 1, @@ -9091,6 +9882,9 @@ "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.75, rate(synapse_storage_events_stale_forward_extremities_persisted_bucket{instance=\"$instance\"}[$bucket_size]) and on (index, instance, job) (synapse_storage_events_persisted_events > 0))", "format": "time_series", "intervalFactor": 1, @@ -9098,6 +9892,9 @@ "refId": "B" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.90, rate(synapse_storage_events_stale_forward_extremities_persisted_bucket{instance=\"$instance\"}[$bucket_size]) and on (index, instance, job) (synapse_storage_events_persisted_events > 0))", "format": "time_series", "intervalFactor": 1, @@ -9105,6 +9902,9 @@ "refId": "C" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.99, rate(synapse_storage_events_stale_forward_extremities_persisted_bucket{instance=\"$instance\"}[$bucket_size]) and on (index, instance, job) (synapse_storage_events_persisted_events > 0))", "format": "time_series", "intervalFactor": 1, @@ -9113,9 +9913,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Events persisted, by number of stale forward extremities in room (quantiles)", "tooltip": { "shared": true, @@ -9124,9 +9922,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -9135,28 +9931,22 @@ "format": "short", "label": "Number of stale forward extremities in room", "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { "cards": { - "cardPadding": 0, - "cardRound": null + "cardPadding": 0 }, "color": { "cardColor": "#73BF69", @@ -9167,7 +9957,9 @@ "mode": "opacity" }, "dataFormat": "tsbuckets", - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "Colour reflects the number of state resolution operations performed over the given number of state groups, or fewer.", "fieldConfig": { "defaults": { @@ -9192,6 +9984,9 @@ "reverseYBuckets": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_state_number_state_groups_in_resolution_bucket{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size])", "format": "heatmap", "interval": "", @@ -9200,8 +9995,6 @@ "refId": "A" } ], - "timeFrom": null, - "timeShift": null, "title": "Number of state resolution performed, by number of state groups involved (heatmap)", "tooltip": { "show": true, @@ -9211,27 +10004,22 @@ "xAxis": { "show": true }, - "xBucketNumber": null, - "xBucketSize": null, "yAxis": { "decimals": 0, "format": "short", "logBase": 1, - "max": null, - "min": null, - "show": true, - "splitFactor": null + "show": true }, - "yBucketBound": "auto", - "yBucketNumber": null, - "yBucketSize": null + "yBucketBound": "auto" }, { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "For a given percentage P, the number X where P% of state resolution operations took place over X state groups or fewer.", "fieldConfig": { "defaults": { @@ -9275,6 +10063,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.5, rate(synapse_state_number_state_groups_in_resolution_bucket{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]))", "format": "time_series", "interval": "", @@ -9283,6 +10074,9 @@ "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.75, rate(synapse_state_number_state_groups_in_resolution_bucket{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]))", "format": "time_series", "interval": "", @@ -9291,6 +10085,9 @@ "refId": "B" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.90, rate(synapse_state_number_state_groups_in_resolution_bucket{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]))", "format": "time_series", "interval": "", @@ -9299,6 +10096,9 @@ "refId": "C" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "histogram_quantile(0.99, rate(synapse_state_number_state_groups_in_resolution_bucket{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]))", "format": "time_series", "interval": "", @@ -9308,9 +10108,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Number of state resolutions performed, by number of state groups involved (quantiles)", "tooltip": { "shared": true, @@ -9319,9 +10117,7 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, @@ -9330,22 +10126,17 @@ "format": "short", "label": "Number of state groups", "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -9353,7 +10144,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "description": "When we do a state res while persisting events we try and see if we can prune any stale extremities.", "fieldConfig": { "defaults": { @@ -9394,18 +10187,27 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_storage_events_state_resolutions_during_persistence{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]))", "interval": "", "legendFormat": "State res ", "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_storage_events_potential_times_prune_extremities{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]))", "interval": "", "legendFormat": "Potential to prune", "refId": "B" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "sum(rate(synapse_storage_events_times_pruned_extremities{instance=\"$instance\",job=~\"$job\",index=~\"$index\"}[$bucket_size]))", "interval": "", "legendFormat": "Pruned", @@ -9413,9 +10215,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Stale extremity dropping", "tooltip": { "shared": true, @@ -9424,47 +10224,50 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" + } + ], "title": "Extremities", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 40 + "y": 41 }, "id": 158, "panels": [ @@ -9473,7 +10276,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {}, @@ -9525,6 +10330,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_admin_mau:current{instance=\"$instance\", job=~\"$job\"}", "format": "time_series", "interval": "", @@ -9533,6 +10341,9 @@ "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_admin_mau:max{instance=\"$instance\", job=~\"$job\"}", "format": "time_series", "interval": "", @@ -9542,9 +10353,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "MAU Limits", "tooltip": { "shared": true, @@ -9553,33 +10362,27 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { + "$$hashKey": "object:176", "format": "short", - "label": null, "logBase": 1, - "max": null, "min": "0", "show": true }, { + "$$hashKey": "object:177", "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -9587,7 +10390,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {} @@ -9630,6 +10435,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "synapse_admin_mau_current_mau_by_service{instance=\"$instance\"}", "interval": "", "legendFormat": "{{ app_service }}", @@ -9637,9 +10445,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "MAU by Appservice", "tooltip": { "shared": true, @@ -9648,47 +10454,50 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" + } + ], "title": "MAU", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 41 + "y": 42 }, "id": 177, "panels": [ @@ -9697,7 +10506,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {}, @@ -9739,6 +10550,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_notifier_users_woken_by_stream{job=\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "format": "time_series", "hide": false, @@ -9750,9 +10564,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Notifier Streams Woken", "tooltip": { "shared": true, @@ -9761,33 +10573,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -9795,7 +10598,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {}, @@ -9837,6 +10642,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_handler_presence_get_updates{job=~\"$job\",instance=\"$instance\"}[$bucket_size])", "format": "time_series", "interval": "", @@ -9847,9 +10655,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Presence Stream Fetch Type Rates", "tooltip": { "shared": true, @@ -9858,47 +10664,51 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, "min": "0", "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" + } + ], "title": "Notifier", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 42 + "y": 43 }, "id": 170, "panels": [ @@ -9907,12 +10717,8 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", - "fieldConfig": { - "defaults": { - "custom": {} - }, - "overrides": [] + "datasource": { + "uid": "$datasource" }, "fill": 1, "fillGradient": 0, @@ -9940,7 +10746,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.3.2", "pointradius": 2, "points": false, "renderer": "flot", @@ -9950,6 +10756,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_appservice_api_sent_events{instance=\"$instance\"}[$bucket_size])", "interval": "", "legendFormat": "{{service}}", @@ -9957,9 +10766,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Sent Events rate", "tooltip": { "shared": true, @@ -9968,33 +10775,26 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { + "$$hashKey": "object:177", "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { + "$$hashKey": "object:178", "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -10002,12 +10802,8 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", - "fieldConfig": { - "defaults": { - "custom": {} - }, - "overrides": [] + "datasource": { + "uid": "$datasource" }, "fill": 1, "fillGradient": 0, @@ -10035,7 +10831,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "8.3.2", "pointradius": 2, "points": false, "renderer": "flot", @@ -10045,16 +10841,17 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_appservice_api_sent_transactions{instance=\"$instance\"}[$bucket_size])", "interval": "", - "legendFormat": "{{service}}", + "legendFormat": "{{exported_service }} {{ service }}", "refId": "A" } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Transactions rate", "tooltip": { "shared": true, @@ -10063,47 +10860,52 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { + "$$hashKey": "object:260", "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { + "$$hashKey": "object:261", "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" + } + ], "title": "Appservices", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 43 + "y": 44 }, "id": 188, "panels": [ @@ -10112,7 +10914,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {} @@ -10155,30 +10959,45 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_handler_presence_notified_presence{job=\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "interval": "", "legendFormat": "Notified", "refId": "A" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_handler_presence_federation_presence_out{job=\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "interval": "", "legendFormat": "Remote ping", "refId": "B" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_handler_presence_presence_updates{job=\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "interval": "", "legendFormat": "Total updates", "refId": "C" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_handler_presence_federation_presence{job=\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "interval": "", "legendFormat": "Remote updates", "refId": "D" }, { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_handler_presence_bump_active_time{job=\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "interval": "", "legendFormat": "Bump active time", @@ -10186,9 +11005,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Presence", "tooltip": { "shared": true, @@ -10197,33 +11014,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -10231,7 +11039,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {} @@ -10274,6 +11084,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_handler_presence_state_transition{job=\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "interval": "", "legendFormat": "{{from}} -> {{to}}", @@ -10281,9 +11094,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Presence state transitions", "tooltip": { "shared": true, @@ -10292,33 +11103,24 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { @@ -10326,7 +11128,9 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "fieldConfig": { "defaults": { "custom": {} @@ -10369,6 +11173,9 @@ "steppedLine": false, "targets": [ { + "datasource": { + "uid": "$datasource" + }, "expr": "rate(synapse_handler_presence_notify_reason{job=\"$job\",index=~\"$index\",instance=\"$instance\"}[$bucket_size])", "interval": "", "legendFormat": "{{reason}}", @@ -10376,9 +11183,7 @@ } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "Presence notify reason", "tooltip": { "shared": true, @@ -10387,165 +11192,162 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { + "$$hashKey": "object:165", "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { + "$$hashKey": "object:166", "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } } ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" + } + ], "title": "Presence", "type": "row" }, { "collapsed": true, - "datasource": "${DS_PROMETHEUS}", + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, "gridPos": { "h": 1, "w": 24, "x": 0, - "y": 44 + "y": 45 }, "id": 197, "panels": [ { - "aliasColors": {}, - "bars": false, - "dashLength": 10, - "dashes": false, - "datasource": "$datasource", + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, "fieldConfig": { "defaults": { - "custom": {} + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "hertz" }, "overrides": [] }, - "fill": 1, - "fillGradient": 0, "gridPos": { "h": 8, "w": 12, "x": 0, - "y": 1 + "y": 46 }, - "hiddenSeries": false, "id": 191, - "legend": { - "avg": false, - "current": false, - "max": false, - "min": false, - "show": true, - "total": false, - "values": false - }, - "lines": true, - "linewidth": 1, - "nullPointMode": "null", "options": { - "alertThreshold": true + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom" + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } }, - "percentage": false, - "pluginVersion": "7.3.7", - "pointradius": 2, - "points": false, - "renderer": "flot", - "seriesOverrides": [], - "spaceLength": 10, - "stack": false, - "steppedLine": false, + "pluginVersion": "9.0.4", "targets": [ { - "expr": "rate(synapse_external_cache_set{job=\"$job\", instance=\"$instance\", index=~\"$index\"}[$bucket_size])", + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "expr": "rate(synapse_external_cache_set{job=~\"$job\", instance=\"$instance\", index=~\"$index\"}[$bucket_size])", "interval": "", - "legendFormat": "{{ cache_name }} {{ index }}", + "legendFormat": "{{ cache_name }} {{job}}-{{ index }}", + "range": true, "refId": "A" } ], - "thresholds": [], - "timeFrom": null, - "timeRegions": [], - "timeShift": null, "title": "External Cache Set Rate", - "tooltip": { - "shared": true, - "sort": 2, - "value_type": "individual" - }, - "type": "graph", - "xaxis": { - "buckets": null, - "mode": "time", - "name": null, - "show": true, - "values": [] - }, - "yaxes": [ - { - "format": "hertz", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - }, - { - "format": "short", - "label": null, - "logBase": 1, - "max": null, - "min": null, - "show": true - } - ], - "yaxis": { - "align": false, - "alignLevel": null - } + "type": "timeseries" }, { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "$datasource", - "description": "", - "fieldConfig": { - "defaults": { - "custom": {} - }, - "overrides": [] + "datasource": { + "type": "prometheus", + "uid": "$datasource" }, + "description": "", "fill": 1, "fillGradient": 0, "gridPos": { "h": 8, "w": 12, "x": 12, - "y": 1 + "y": 46 }, "hiddenSeries": false, "id": 193, @@ -10565,7 +11367,7 @@ "alertThreshold": true }, "percentage": false, - "pluginVersion": "7.3.7", + "pluginVersion": "9.0.4", "pointradius": 2, "points": false, "renderer": "flot", @@ -10575,16 +11377,19 @@ "steppedLine": false, "targets": [ { - "expr": "rate(synapse_external_cache_get{job=\"$job\", instance=\"$instance\", index=~\"$index\"}[$bucket_size])", + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "expr": "sum without (hit) (rate(synapse_external_cache_get{job=~\"$job\", instance=\"$instance\", index=~\"$index\"}[$bucket_size]))", "interval": "", - "legendFormat": "{{ cache_name }} {{ index }}", + "legendFormat": "{{ cache_name }} {{job}}-{{ index }}", + "range": true, "refId": "A" } ], "thresholds": [], - "timeFrom": null, "timeRegions": [], - "timeShift": null, "title": "External Cache Get Rate", "tooltip": { "shared": true, @@ -10593,39 +11398,31 @@ }, "type": "graph", "xaxis": { - "buckets": null, "mode": "time", - "name": null, "show": true, "values": [] }, "yaxes": [ { + "$$hashKey": "object:390", "format": "hertz", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true }, { + "$$hashKey": "object:391", "format": "short", - "label": null, "logBase": 1, - "max": null, - "min": null, "show": true } ], "yaxis": { - "align": false, - "alignLevel": null + "align": false } }, { "cards": { - "cardPadding": -1, - "cardRound": null + "cardPadding": -1 }, "color": { "cardColor": "#b4ff00", @@ -10636,18 +11433,15 @@ "mode": "spectrum" }, "dataFormat": "tsbuckets", - "datasource": "$datasource", - "fieldConfig": { - "defaults": { - "custom": {} - }, - "overrides": [] + "datasource": { + "type": "prometheus", + "uid": "$datasource" }, "gridPos": { - "h": 9, + "h": 8, "w": 12, "x": 0, - "y": 9 + "y": 54 }, "heatmap": {}, "hideZeroBuckets": false, @@ -10660,7 +11454,10 @@ "reverseYBuckets": false, "targets": [ { - "expr": "sum(rate(synapse_external_cache_response_time_seconds_bucket{index=~\"$index\",instance=\"$instance\",job=\"$job\"}[$bucket_size])) by (le)", + "datasource": { + "uid": "$datasource" + }, + "expr": "sum(rate(synapse_external_cache_response_time_seconds_bucket{index=~\"$index\",instance=\"$instance\",job=~\"$job\"}[$bucket_size])) by (le)", "format": "heatmap", "instant": false, "interval": "", @@ -10679,20 +11476,109 @@ "xAxis": { "show": true }, - "xBucketNumber": null, - "xBucketSize": null, "yAxis": { "decimals": 0, "format": "s", "logBase": 1, - "max": null, - "min": null, - "show": true, - "splitFactor": null + "show": true + }, + "yBucketBound": "auto" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$datasource" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + } + ] + }, + "unit": "hertz" + }, + "overrides": [] }, - "yBucketBound": "auto", - "yBucketNumber": null, - "yBucketSize": null + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 54 + }, + "id": 223, + "options": { + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom" + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "9.0.4", + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "editorMode": "code", + "expr": "rate(synapse_external_cache_get{job=~\"$job\", instance=\"$instance\", index=~\"$index\", hit=\"False\"}[$bucket_size])", + "interval": "", + "legendFormat": "{{ cache_name }} {{job}}-{{ index }}", + "range": true, + "refId": "A" + } + ], + "title": "External Cache Miss Rate", + "type": "timeseries" + } + ], + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "000000001" + }, + "refId": "A" } ], "title": "External Cache", @@ -10700,7 +11586,7 @@ } ], "refresh": false, - "schemaVersion": 26, + "schemaVersion": 36, "style": "dark", "tags": [ "matrix" @@ -10713,10 +11599,8 @@ "text": "default", "value": "default" }, - "error": null, "hide": 0, "includeAll": false, - "label": null, "multi": false, "name": "datasource", "options": [], @@ -10731,14 +11615,12 @@ "allFormat": "glob", "auto": true, "auto_count": 100, - "auto_min": "60s", + "auto_min": "30s", "current": { "selected": false, "text": "auto", "value": "$__auto_interval_bucket_size" }, - "datasource": null, - "error": null, "hide": 0, "includeAll": false, "label": "Bucket Size", @@ -10789,24 +11671,25 @@ "type": "interval" }, { - "allValue": null, "current": {}, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "definition": "", - "error": null, "hide": 0, "includeAll": false, - "label": null, "multi": false, "name": "instance", "options": [], - "query": "label_values(synapse_util_metrics_block_ru_utime_seconds, instance)", + "query": { + "query": "label_values(synapse_util_metrics_block_ru_utime_seconds, instance)", + "refId": "Prometheus-instance-Variable-Query" + }, "refresh": 2, "regex": "", "skipUrlSync": false, "sort": 1, "tagValuesQuery": "", - "tags": [], "tagsQuery": "", "type": "query", "useTags": false @@ -10815,9 +11698,10 @@ "allFormat": "regex wildcard", "allValue": "", "current": {}, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "definition": "", - "error": null, "hide": 0, "hideLabel": false, "includeAll": true, @@ -10826,14 +11710,16 @@ "multiFormat": "regex values", "name": "job", "options": [], - "query": "label_values(synapse_util_metrics_block_ru_utime_seconds, job)", + "query": { + "query": "label_values(synapse_util_metrics_block_ru_utime_seconds, job)", + "refId": "Prometheus-job-Variable-Query" + }, "refresh": 2, "refresh_on_load": false, "regex": "", "skipUrlSync": false, "sort": 1, "tagValuesQuery": "", - "tags": [], "tagsQuery": "", "type": "query", "useTags": false @@ -10842,9 +11728,10 @@ "allFormat": "regex wildcard", "allValue": ".*", "current": {}, - "datasource": "$datasource", + "datasource": { + "uid": "$datasource" + }, "definition": "", - "error": null, "hide": 0, "hideLabel": false, "includeAll": true, @@ -10853,14 +11740,16 @@ "multiFormat": "regex values", "name": "index", "options": [], - "query": "label_values(synapse_util_metrics_block_ru_utime_seconds, index)", + "query": { + "query": "label_values(synapse_util_metrics_block_ru_utime_seconds, index)", + "refId": "Prometheus-index-Variable-Query" + }, "refresh": 2, "refresh_on_load": false, "regex": "", "skipUrlSync": false, "sort": 3, "tagValuesQuery": "", - "tags": [], "tagsQuery": "", "type": "query", "useTags": false @@ -10868,8 +11757,8 @@ ] }, "time": { - "from": "now-3h", - "to": "now" + "from": "2022-07-22T04:08:13.716Z", + "to": "2022-07-22T18:44:27.863Z" }, "timepicker": { "now": true, @@ -10900,5 +11789,6 @@ "timezone": "", "title": "Synapse", "uid": "000000012", - "version": 100 -} + "version": 124, + "weekStart": "" +} \ No newline at end of file diff --git a/debian/changelog b/debian/changelog index 21115d7be2..c3974261a9 100644 --- a/debian/changelog +++ b/debian/changelog @@ -1,3 +1,15 @@ +matrix-synapse-py3 (1.66.0~rc1) stable; urgency=medium + + * New Synapse release 1.66.0rc1. + + -- Synapse Packaging team <packages@matrix.org> Tue, 23 Aug 2022 09:48:55 +0100 + +matrix-synapse-py3 (1.65.0) stable; urgency=medium + + * New Synapse release 1.65.0. + + -- Synapse Packaging team <packages@matrix.org> Tue, 16 Aug 2022 16:51:26 +0100 + matrix-synapse-py3 (1.65.0~rc2) stable; urgency=medium * New Synapse release 1.65.0rc2. diff --git a/docker/README.md b/docker/README.md index 5b7de2fe38..017f046c58 100644 --- a/docker/README.md +++ b/docker/README.md @@ -191,7 +191,7 @@ If you need to build the image from a Synapse checkout, use the following `docke build` command from the repo's root: ``` -docker build -t matrixdotorg/synapse -f docker/Dockerfile . +DOCKER_BUILDKIT=1 docker build -t matrixdotorg/synapse -f docker/Dockerfile . ``` You can choose to build a different docker image by changing the value of the `-f` flag to diff --git a/docs/admin_api/rooms.md b/docs/admin_api/rooms.md index 9aa489e4a3..7526956bec 100644 --- a/docs/admin_api/rooms.md +++ b/docs/admin_api/rooms.md @@ -302,6 +302,8 @@ The following fields are possible in the JSON response body: * `state_events` - Total number of state_events of a room. Complexity of the room. * `room_type` - The type of the room taken from the room's creation event; for example "m.space" if the room is a space. If the room does not define a type, the value will be `null`. +* `forgotten` - Whether all local users have + [forgotten](https://spec.matrix.org/latest/client-server-api/#leaving-rooms) the room. The API is: @@ -330,10 +332,13 @@ A response body like the following is returned: "guest_access": null, "history_visibility": "shared", "state_events": 93534, - "room_type": "m.space" + "room_type": "m.space", + "forgotten": false } ``` +_Changed in Synapse 1.66:_ Added the `forgotten` key to the response body. + # Room Members API The Room Members admin API allows server admins to get a list of all members of a room. diff --git a/docs/admin_api/user_admin_api.md b/docs/admin_api/user_admin_api.md index 0871cfebf5..c1ca0c8a64 100644 --- a/docs/admin_api/user_admin_api.md +++ b/docs/admin_api/user_admin_api.md @@ -753,6 +753,7 @@ A response body like the following is returned: "device_id": "QBUAZIFURK", "display_name": "android", "last_seen_ip": "1.2.3.4", + "last_seen_user_agent": "Mozilla/5.0 (X11; Linux x86_64; rv:103.0) Gecko/20100101 Firefox/103.0", "last_seen_ts": 1474491775024, "user_id": "<user_id>" }, @@ -760,6 +761,7 @@ A response body like the following is returned: "device_id": "AUIECTSRND", "display_name": "ios", "last_seen_ip": "1.2.3.5", + "last_seen_user_agent": "Mozilla/5.0 (X11; Linux x86_64; rv:103.0) Gecko/20100101 Firefox/103.0", "last_seen_ts": 1474491775025, "user_id": "<user_id>" } @@ -786,6 +788,8 @@ The following fields are returned in the JSON response body: Absent if no name has been set. - `last_seen_ip` - The IP address where this device was last seen. (May be a few minutes out of date, for efficiency reasons). + - `last_seen_user_agent` - The user agent of the device when it was last seen. + (May be a few minutes out of date, for efficiency reasons). - `last_seen_ts` - The timestamp (in milliseconds since the unix epoch) when this devices was last seen. (May be a few minutes out of date, for efficiency reasons). - `user_id` - Owner of device. @@ -837,6 +841,7 @@ A response body like the following is returned: "device_id": "<device_id>", "display_name": "android", "last_seen_ip": "1.2.3.4", + "last_seen_user_agent": "Mozilla/5.0 (X11; Linux x86_64; rv:103.0) Gecko/20100101 Firefox/103.0", "last_seen_ts": 1474491775024, "user_id": "<user_id>" } @@ -858,6 +863,8 @@ The following fields are returned in the JSON response body: Absent if no name has been set. - `last_seen_ip` - The IP address where this device was last seen. (May be a few minutes out of date, for efficiency reasons). + - `last_seen_user_agent` - The user agent of the device when it was last seen. + (May be a few minutes out of date, for efficiency reasons). - `last_seen_ts` - The timestamp (in milliseconds since the unix epoch) when this devices was last seen. (May be a few minutes out of date, for efficiency reasons). - `user_id` - Owner of device. diff --git a/docs/auth_chain_difference_algorithm.md b/docs/auth_chain_difference_algorithm.md index 30f72a70da..ebc9de25b8 100644 --- a/docs/auth_chain_difference_algorithm.md +++ b/docs/auth_chain_difference_algorithm.md @@ -34,13 +34,45 @@ the process of indexing it). ## Chain Cover Index Synapse computes auth chain differences by pre-computing a "chain cover" index -for the auth chain in a room, allowing efficient reachability queries like "is -event A in the auth chain of event B". This is done by assigning every event a -*chain ID* and *sequence number* (e.g. `(5,3)`), and having a map of *links* -between chains (e.g. `(5,3) -> (2,4)`) such that A is reachable by B (i.e. `A` -is in the auth chain of `B`) if and only if either: - -1. A and B have the same chain ID and `A`'s sequence number is less than `B`'s +for the auth chain in a room, allowing us to efficiently make reachability queries +like "is event `A` in the auth chain of event `B`?". We could do this with an index +that tracks all pairs `(A, B)` such that `A` is in the auth chain of `B`. However, this +would be prohibitively large, scaling poorly as the room accumulates more state +events. + +Instead, we break down the graph into *chains*. A chain is a subset of a DAG +with the following property: for any pair of events `E` and `F` in the chain, +the chain contains a path `E -> F` or a path `F -> E`. This forces a chain to be +linear (without forks), e.g. `E -> F -> G -> ... -> H`. Each event in the chain +is given a *sequence number* local to that chain. The oldest event `E` in the +chain has sequence number 1. If `E` has a child `F` in the chain, then `F` has +sequence number 2. If `E` has a grandchild `G` in the chain, then `G` has +sequence number 3; and so on. + +Synapse ensures that each persisted event belongs to exactly one chain, and +tracks how the chains are connected to one another. This allows us to +efficiently answer reachability queries. Doing so uses less storage than +tracking reachability on an event-by-event basis, particularly when we have +fewer and longer chains. See + +> Jagadish, H. (1990). [A compression technique to materialize transitive closure](https://doi.org/10.1145/99935.99944). +> *ACM Transactions on Database Systems (TODS)*, 15*(4)*, 558-598. + +for the original idea or + +> Y. Chen, Y. Chen, [An efficient algorithm for answering graph +> reachability queries](https://doi.org/10.1109/ICDE.2008.4497498), +> in: 2008 IEEE 24th International Conference on Data Engineering, April 2008, +> pp. 893–902. (PDF available via [Google Scholar](https://scholar.google.com/scholar?q=Y.%20Chen,%20Y.%20Chen,%20An%20efficient%20algorithm%20for%20answering%20graph%20reachability%20queries,%20in:%202008%20IEEE%2024th%20International%20Conference%20on%20Data%20Engineering,%20April%202008,%20pp.%20893902.).) + +for a more modern take. + +In practical terms, the chain cover assigns every event a +*chain ID* and *sequence number* (e.g. `(5,3)`), and maintains a map of *links* +between events in chains (e.g. `(5,3) -> (2,4)`) such that `A` is reachable by `B` +(i.e. `A` is in the auth chain of `B`) if and only if either: + +1. `A` and `B` have the same chain ID and `A`'s sequence number is less than `B`'s sequence number; or 2. there is a link `L` between `B`'s chain ID and `A`'s chain ID such that `L.start_seq_no` <= `B.seq_no` and `A.seq_no` <= `L.end_seq_no`. @@ -49,8 +81,9 @@ There are actually two potential implementations, one where we store links from each chain to every other reachable chain (the transitive closure of the links graph), and one where we remove redundant links (the transitive reduction of the links graph) e.g. if we have chains `C3 -> C2 -> C1` then the link `C3 -> C1` -would not be stored. Synapse uses the former implementations so that it doesn't -need to recurse to test reachability between chains. +would not be stored. Synapse uses the former implementation so that it doesn't +need to recurse to test reachability between chains. This trades-off extra storage +in order to save CPU cycles and DB queries. ### Example diff --git a/docs/message_retention_policies.md b/docs/message_retention_policies.md index 8c88f93935..7f3e5359f1 100644 --- a/docs/message_retention_policies.md +++ b/docs/message_retention_policies.md @@ -8,7 +8,8 @@ and allow server and room admins to configure how long messages should be kept in a homeserver's database before being purged from it. **Please note that, as this feature isn't part of the Matrix specification yet, this implementation is to be considered as -experimental.** +experimental. There are known bugs which may cause database corruption. +Proceed with caution.** A message retention policy is mainly defined by its `max_lifetime` parameter, which defines how long a message can be kept around after diff --git a/docs/openid.md b/docs/openid.md index d0ccf36f71..ce9b026228 100644 --- a/docs/openid.md +++ b/docs/openid.md @@ -174,7 +174,9 @@ oidc_providers: 1. Create a regular web application for Synapse 2. Set the Allowed Callback URLs to `[synapse public baseurl]/_synapse/client/oidc/callback` -3. Add a rule to add the `preferred_username` claim. +3. Add a rule with any name to add the `preferred_username` claim. +(See https://auth0.com/docs/customize/rules/create-rules for more information on how to create rules.) + <details> <summary>Code sample</summary> diff --git a/docs/templates.md b/docs/templates.md index f87692a453..453ac90dd8 100644 --- a/docs/templates.md +++ b/docs/templates.md @@ -9,7 +9,7 @@ in, allowing them to specify custom templates: ```yaml templates: - custom_templates_directory: /path/to/custom/templates/ + custom_template_directory: /path/to/custom/templates/ ``` If this setting is not set, or the files named below are not found within the directory, diff --git a/docs/upgrade.md b/docs/upgrade.md index 47a74b67de..0ab5bfeaf0 100644 --- a/docs/upgrade.md +++ b/docs/upgrade.md @@ -89,6 +89,25 @@ process, for example: dpkg -i matrix-synapse-py3_1.3.0+stretch1_amd64.deb ``` +# Upgrading to v1.66.0 + +## Delegation of email validation no longer supported + +As of this version, Synapse no longer allows the tasks of verifying email address +ownership, and password reset confirmation, to be delegated to an identity server. +This removal was previously planned for Synapse 1.64.0, but was +[delayed](https://github.com/matrix-org/synapse/issues/13421) until now to give +homeserver administrators more notice of the change. + +To continue to allow users to add email addresses to their homeserver accounts, +and perform password resets, make sure that Synapse is configured with a working +email server in the [`email` configuration +section](https://matrix-org.github.io/synapse/latest/usage/configuration/config_documentation.html#email) +(including, at a minimum, a `notif_from` setting.) + +Specifying an `email` setting under `account_threepid_delegates` will now cause +an error at startup. + # Upgrading to v1.64.0 ## Deprecation of the ability to delegate e-mail verification to identity servers diff --git a/docs/usage/administration/admin_faq.md b/docs/usage/administration/admin_faq.md index 3dcad4bbef..7ba5a83f04 100644 --- a/docs/usage/administration/admin_faq.md +++ b/docs/usage/administration/admin_faq.md @@ -2,9 +2,9 @@ How do I become a server admin? --- -If your server already has an admin account you should use the user admin API to promote other accounts to become admins. See [User Admin API](../../admin_api/user_admin_api.md#Change-whether-a-user-is-a-server-administrator-or-not) +If your server already has an admin account you should use the [User Admin API](../../admin_api/user_admin_api.md#Change-whether-a-user-is-a-server-administrator-or-not) to promote other accounts to become admins. -If you don't have any admin accounts yet you won't be able to use the admin API so you'll have to edit the database manually. Manually editing the database is generally not recommended so once you have an admin account, use the admin APIs to make further changes. +If you don't have any admin accounts yet you won't be able to use the admin API, so you'll have to edit the database manually. Manually editing the database is generally not recommended so once you have an admin account: use the admin APIs to make further changes. ```sql UPDATE users SET admin = 1 WHERE name = '@foo:bar.com'; @@ -32,9 +32,11 @@ What users are registered on my server? SELECT NAME from users; ``` -Manually resetting passwords: +Manually resetting passwords --- -See https://github.com/matrix-org/synapse/blob/master/README.rst#password-reset +Users can reset their password through their client. Alternatively, a server admin +can reset a user's password using the [admin API](../../admin_api/user_admin_api.md#reset-password). + I have a problem with my server. Can I just delete my database and start again? --- @@ -101,3 +103,83 @@ LIMIT 10; You can also use the [List Room API](../../admin_api/rooms.md#list-room-api) and `order_by` `state_events`. + + +People can't accept room invitations from me +--- + +The typical failure mode here is that you send an invitation to someone +to join a room or direct chat, but when they go to accept it, they get an +error (typically along the lines of "Invalid signature"). They might see +something like the following in their logs: + + 2019-09-11 19:32:04,271 - synapse.federation.transport.server - 288 - WARNING - GET-11752 - authenticate_request failed: 401: Invalid signature for server <server> with key ed25519:a_EqML: Unable to verify signature for <server> + +This is normally caused by a misconfiguration in your reverse-proxy. See [the reverse proxy docs](docs/reverse_proxy.md) and double-check that your settings are correct. + + +Help!! Synapse is slow and eats all my RAM/CPU! +----------------------------------------------- + +First, ensure you are running the latest version of Synapse, using Python 3 +with a [PostgreSQL database](../../postgres.md). + +Synapse's architecture is quite RAM hungry currently - we deliberately +cache a lot of recent room data and metadata in RAM in order to speed up +common requests. We'll improve this in the future, but for now the easiest +way to either reduce the RAM usage (at the risk of slowing things down) +is to set the almost-undocumented ``SYNAPSE_CACHE_FACTOR`` environment +variable. The default is 0.5, which can be decreased to reduce RAM usage +in memory constrained environments, or increased if performance starts to +degrade. + +However, degraded performance due to a low cache factor, common on +machines with slow disks, often leads to explosions in memory use due +backlogged requests. In this case, reducing the cache factor will make +things worse. Instead, try increasing it drastically. 2.0 is a good +starting value. + +Using [libjemalloc](https://jemalloc.net) can also yield a significant +improvement in overall memory use, and especially in terms of giving back +RAM to the OS. To use it, the library must simply be put in the +LD_PRELOAD environment variable when launching Synapse. On Debian, this +can be done by installing the `libjemalloc1` package and adding this +line to `/etc/default/matrix-synapse`: + + LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libjemalloc.so.1 + +This made a significant difference on Python 2.7 - it's unclear how +much of an improvement it provides on Python 3.x. + +If you're encountering high CPU use by the Synapse process itself, you +may be affected by a bug with presence tracking that leads to a +massive excess of outgoing federation requests (see [discussion](https://github.com/matrix-org/synapse/issues/3971)). If metrics +indicate that your server is also issuing far more outgoing federation +requests than can be accounted for by your users' activity, this is a +likely cause. The misbehavior can be worked around by disabling presence +in the Synapse config file: [see here](../configuration/config_documentation.md#presence). + + +Running out of File Handles +--------------------------- + +If Synapse runs out of file handles, it typically fails badly - live-locking +at 100% CPU, and/or failing to accept new TCP connections (blocking the +connecting client). Matrix currently can legitimately use a lot of file handles, +thanks to busy rooms like `#matrix:matrix.org` containing hundreds of participating +servers. The first time a server talks in a room it will try to connect +simultaneously to all participating servers, which could exhaust the available +file descriptors between DNS queries & HTTPS sockets, especially if DNS is slow +to respond. (We need to improve the routing algorithm used to be better than +full mesh, but as of March 2019 this hasn't happened yet). + +If you hit this failure mode, we recommend increasing the maximum number of +open file handles to be at least 4096 (assuming a default of 1024 or 256). +This is typically done by editing ``/etc/security/limits.conf`` + +Separately, Synapse may leak file handles if inbound HTTP requests get stuck +during processing - e.g. blocked behind a lock or talking to a remote server etc. +This is best diagnosed by matching up the 'Received request' and 'Processed request' +log lines and looking for any 'Processed request' lines which take more than +a few seconds to execute. Please let us know at [`#synapse:matrix.org`](https://matrix.to/#/#synapse-dev:matrix.org) if +you see this failure mode so we can help debug it, however. diff --git a/docs/usage/configuration/config_documentation.md b/docs/usage/configuration/config_documentation.md index bc3d2bec6a..8ae018e628 100644 --- a/docs/usage/configuration/config_documentation.md +++ b/docs/usage/configuration/config_documentation.md @@ -444,7 +444,7 @@ Sub-options for each listener include: * `names`: a list of names of HTTP resources. See below for a list of valid resource names. * `compress`: set to true to enable gzip compression on HTTP bodies for this resource. This is currently only supported with the - `client`, `consent` and `metrics` resources. + `client`, `consent`, `metrics` and `federation` resources. * `additional_resources`: Only valid for an 'http' listener. A map of additional endpoints which should be loaded via dynamic modules. @@ -849,7 +849,11 @@ which are older than the room's maximum retention period. Synapse will also filter events received over federation so that events that should have been purged are ignored and not stored again. -The message retention policies feature is disabled by default. +The message retention policies feature is disabled by default. Please be advised +that enabling this feature carries some risk. There are known bugs with the implementation +which can cause database corruption. Setting retention to delete older history +is less risky than deleting newer history but in general caution is advised when enabling this +experimental feature. You can read more about this feature [here](../../message_retention_policies.md). This setting has the following sub-options: * `default_policy`: Default retention policy. If set, Synapse will apply it to rooms that lack the @@ -2178,7 +2182,10 @@ their account. by the Matrix Identity Service API [specification](https://matrix.org/docs/spec/identity_service/latest).) -*Updated in Synapse 1.64.0*: The `email` option is deprecated. +*Deprecated in Synapse 1.64.0*: The `email` option is deprecated. + +*Removed in Synapse 1.66.0*: The `email` option has been removed. +If present, Synapse will report a configuration error on startup. Example configuration: ```yaml @@ -3348,7 +3355,7 @@ user_directory: For detailed instructions on user consent configuration, see [here](../../consent_tracking.md). Parts of this section are required if enabling the `consent` resource under -`listeners`, in particular `template_dir` and `version`. # TODO: link `listeners` +[`listeners`](#listeners), in particular `template_dir` and `version`. * `template_dir`: gives the location of the templates for the HTML forms. This directory should contain one subdirectory per language (eg, `en`, `fr`), @@ -3360,7 +3367,7 @@ Parts of this section are required if enabling the `consent` resource under parameter. * `server_notice_content`: if enabled, will send a user a "Server Notice" - asking them to consent to the privacy policy. The `server_notices` section ##TODO: link + asking them to consent to the privacy policy. The [`server_notices` section](#server_notices) must also be configured for this to work. Notices will *not* be sent to guest users unless `send_server_notice_to_guests` is set to true. diff --git a/mypy.ini b/mypy.ini index 6add272990..e2034e411f 100644 --- a/mypy.ini +++ b/mypy.ini @@ -1,6 +1,6 @@ [mypy] namespace_packages = True -plugins = mypy_zope:plugin, scripts-dev/mypy_synapse_plugin.py +plugins = pydantic.mypy, mypy_zope:plugin, scripts-dev/mypy_synapse_plugin.py follow_imports = normal check_untyped_defs = True show_error_codes = True diff --git a/poetry.lock b/poetry.lock index 1acdb5da56..651659ec98 100644 --- a/poetry.lock +++ b/poetry.lock @@ -779,6 +779,21 @@ optional = false python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*" [[package]] +name = "pydantic" +version = "1.9.1" +description = "Data validation and settings management using python type hints" +category = "main" +optional = false +python-versions = ">=3.6.1" + +[package.dependencies] +typing-extensions = ">=3.7.4.3" + +[package.extras] +dotenv = ["python-dotenv (>=0.10.4)"] +email = ["email-validator (>=1.0.3)"] + +[[package]] name = "pyflakes" version = "2.4.0" description = "passive checker of Python programs" @@ -1563,7 +1578,7 @@ url_preview = ["lxml"] [metadata] lock-version = "1.1" python-versions = "^3.7.1" -content-hash = "c24bbcee7e86dbbe7cdbf49f91a25b310bf21095452641e7440129f59b077f78" +content-hash = "7de518bf27967b3547eab8574342cfb67f87d6b47b4145c13de11112141dbf2d" [metadata.files] attrs = [ @@ -2260,6 +2275,43 @@ pycparser = [ {file = "pycparser-2.21-py2.py3-none-any.whl", hash = "sha256:8ee45429555515e1f6b185e78100aea234072576aa43ab53aefcae078162fca9"}, {file = "pycparser-2.21.tar.gz", hash = "sha256:e644fdec12f7872f86c58ff790da456218b10f863970249516d60a5eaca77206"}, ] +pydantic = [ + {file = "pydantic-1.9.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c8098a724c2784bf03e8070993f6d46aa2eeca031f8d8a048dff277703e6e193"}, + {file = "pydantic-1.9.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:c320c64dd876e45254bdd350f0179da737463eea41c43bacbee9d8c9d1021f11"}, + {file = "pydantic-1.9.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:18f3e912f9ad1bdec27fb06b8198a2ccc32f201e24174cec1b3424dda605a310"}, + {file = "pydantic-1.9.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c11951b404e08b01b151222a1cb1a9f0a860a8153ce8334149ab9199cd198131"}, + {file = "pydantic-1.9.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:8bc541a405423ce0e51c19f637050acdbdf8feca34150e0d17f675e72d119580"}, + {file = "pydantic-1.9.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:e565a785233c2d03724c4dc55464559639b1ba9ecf091288dd47ad9c629433bd"}, + {file = "pydantic-1.9.1-cp310-cp310-win_amd64.whl", hash = "sha256:a4a88dcd6ff8fd47c18b3a3709a89adb39a6373f4482e04c1b765045c7e282fd"}, + {file = "pydantic-1.9.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:447d5521575f18e18240906beadc58551e97ec98142266e521c34968c76c8761"}, + {file = "pydantic-1.9.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:985ceb5d0a86fcaa61e45781e567a59baa0da292d5ed2e490d612d0de5796918"}, + {file = "pydantic-1.9.1-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:059b6c1795170809103a1538255883e1983e5b831faea6558ef873d4955b4a74"}, + {file = "pydantic-1.9.1-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:d12f96b5b64bec3f43c8e82b4aab7599d0157f11c798c9f9c528a72b9e0b339a"}, + {file = "pydantic-1.9.1-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:ae72f8098acb368d877b210ebe02ba12585e77bd0db78ac04a1ee9b9f5dd2166"}, + {file = "pydantic-1.9.1-cp36-cp36m-win_amd64.whl", hash = "sha256:79b485767c13788ee314669008d01f9ef3bc05db9ea3298f6a50d3ef596a154b"}, + {file = "pydantic-1.9.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:494f7c8537f0c02b740c229af4cb47c0d39840b829ecdcfc93d91dcbb0779892"}, + {file = "pydantic-1.9.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f0f047e11febe5c3198ed346b507e1d010330d56ad615a7e0a89fae604065a0e"}, + {file = "pydantic-1.9.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:969dd06110cb780da01336b281f53e2e7eb3a482831df441fb65dd30403f4608"}, + {file = "pydantic-1.9.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:177071dfc0df6248fd22b43036f936cfe2508077a72af0933d0c1fa269b18537"}, + {file = "pydantic-1.9.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:9bcf8b6e011be08fb729d110f3e22e654a50f8a826b0575c7196616780683380"}, + {file = "pydantic-1.9.1-cp37-cp37m-win_amd64.whl", hash = "sha256:a955260d47f03df08acf45689bd163ed9df82c0e0124beb4251b1290fa7ae728"}, + {file = "pydantic-1.9.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9ce157d979f742a915b75f792dbd6aa63b8eccaf46a1005ba03aa8a986bde34a"}, + {file = "pydantic-1.9.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:0bf07cab5b279859c253d26a9194a8906e6f4a210063b84b433cf90a569de0c1"}, + {file = "pydantic-1.9.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5d93d4e95eacd313d2c765ebe40d49ca9dd2ed90e5b37d0d421c597af830c195"}, + {file = "pydantic-1.9.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1542636a39c4892c4f4fa6270696902acb186a9aaeac6f6cf92ce6ae2e88564b"}, + {file = "pydantic-1.9.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:a9af62e9b5b9bc67b2a195ebc2c2662fdf498a822d62f902bf27cccb52dbbf49"}, + {file = "pydantic-1.9.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:fe4670cb32ea98ffbf5a1262f14c3e102cccd92b1869df3bb09538158ba90fe6"}, + {file = "pydantic-1.9.1-cp38-cp38-win_amd64.whl", hash = "sha256:9f659a5ee95c8baa2436d392267988fd0f43eb774e5eb8739252e5a7e9cf07e0"}, + {file = "pydantic-1.9.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:b83ba3825bc91dfa989d4eed76865e71aea3a6ca1388b59fc801ee04c4d8d0d6"}, + {file = "pydantic-1.9.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:1dd8fecbad028cd89d04a46688d2fcc14423e8a196d5b0a5c65105664901f810"}, + {file = "pydantic-1.9.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:02eefd7087268b711a3ff4db528e9916ac9aa18616da7bca69c1871d0b7a091f"}, + {file = "pydantic-1.9.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7eb57ba90929bac0b6cc2af2373893d80ac559adda6933e562dcfb375029acee"}, + {file = "pydantic-1.9.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:4ce9ae9e91f46c344bec3b03d6ee9612802682c1551aaf627ad24045ce090761"}, + {file = "pydantic-1.9.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:72ccb318bf0c9ab97fc04c10c37683d9eea952ed526707fabf9ac5ae59b701fd"}, + {file = "pydantic-1.9.1-cp39-cp39-win_amd64.whl", hash = "sha256:61b6760b08b7c395975d893e0b814a11cf011ebb24f7d869e7118f5a339a82e1"}, + {file = "pydantic-1.9.1-py3-none-any.whl", hash = "sha256:4988c0f13c42bfa9ddd2fe2f569c9d54646ce84adc5de84228cfe83396f3bd58"}, + {file = "pydantic-1.9.1.tar.gz", hash = "sha256:1ed987c3ff29fff7fd8c3ea3a3ea877ad310aae2ef9889a119e22d3f2db0691a"}, +] pyflakes = [ {file = "pyflakes-2.4.0-py2.py3-none-any.whl", hash = "sha256:3bb3a3f256f4b7968c9c788781e4ff07dce46bdf12339dcda61053375426ee2e"}, {file = "pyflakes-2.4.0.tar.gz", hash = "sha256:05a85c2872edf37a4ed30b0cce2f6093e1d0581f8c19d7393122da7e25b2b24c"}, diff --git a/pyproject.toml b/pyproject.toml index a9f59a676f..745b6067aa 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -54,7 +54,7 @@ skip_gitignore = true [tool.poetry] name = "matrix-synapse" -version = "1.65.0rc2" +version = "1.66.0rc1" description = "Homeserver for the Matrix decentralised comms protocol" authors = ["Matrix.org Team and Contributors <packages@matrix.org>"] license = "Apache-2.0" @@ -158,6 +158,9 @@ packaging = ">=16.1" # At the time of writing, we only use functions from the version `importlib.metadata` # which shipped in Python 3.8. This corresponds to version 1.4 of the backport. importlib_metadata = { version = ">=1.4", python = "<3.8" } +# This is the most recent version of Pydantic with available on common distros. +pydantic = ">=1.7.4" + # Optional Dependencies diff --git a/scripts-dev/check_pydantic_models.py b/scripts-dev/check_pydantic_models.py new file mode 100755 index 0000000000..d0fb811bdb --- /dev/null +++ b/scripts-dev/check_pydantic_models.py @@ -0,0 +1,425 @@ +#! /usr/bin/env python +# Copyright 2022 The Matrix.org Foundation C.I.C. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +""" +A script which enforces that Synapse always uses strict types when defining a Pydantic +model. + +Pydantic does not yet offer a strict mode, but it is planned for pydantic v2. See + + https://github.com/pydantic/pydantic/issues/1098 + https://pydantic-docs.helpmanual.io/blog/pydantic-v2/#strict-mode + +until then, this script is a best effort to stop us from introducing type coersion bugs +(like the infamous stringy power levels fixed in room version 10). +""" +import argparse +import contextlib +import functools +import importlib +import logging +import os +import pkgutil +import sys +import textwrap +import traceback +import unittest.mock +from contextlib import contextmanager +from typing import Any, Callable, Dict, Generator, List, Set, Type, TypeVar + +from parameterized import parameterized +from pydantic import BaseModel as PydanticBaseModel, conbytes, confloat, conint, constr +from pydantic.typing import get_args +from typing_extensions import ParamSpec + +logger = logging.getLogger(__name__) + +CONSTRAINED_TYPE_FACTORIES_WITH_STRICT_FLAG: List[Callable] = [ + constr, + conbytes, + conint, + confloat, +] + +TYPES_THAT_PYDANTIC_WILL_COERCE_TO = [ + str, + bytes, + int, + float, + bool, +] + + +P = ParamSpec("P") +R = TypeVar("R") + + +class ModelCheckerException(Exception): + """Dummy exception. Allows us to detect unwanted types during a module import.""" + + +class MissingStrictInConstrainedTypeException(ModelCheckerException): + factory_name: str + + def __init__(self, factory_name: str): + self.factory_name = factory_name + + +class FieldHasUnwantedTypeException(ModelCheckerException): + message: str + + def __init__(self, message: str): + self.message = message + + +def make_wrapper(factory: Callable[P, R]) -> Callable[P, R]: + """We patch `constr` and friends with wrappers that enforce strict=True.""" + + @functools.wraps(factory) + def wrapper(*args: P.args, **kwargs: P.kwargs) -> R: + # type-ignore: should be redundant once we can use https://github.com/python/mypy/pull/12668 + if "strict" not in kwargs: # type: ignore[attr-defined] + raise MissingStrictInConstrainedTypeException(factory.__name__) + if not kwargs["strict"]: # type: ignore[index] + raise MissingStrictInConstrainedTypeException(factory.__name__) + return factory(*args, **kwargs) + + return wrapper + + +def field_type_unwanted(type_: Any) -> bool: + """Very rough attempt to detect if a type is unwanted as a Pydantic annotation. + + At present, we exclude types which will coerce, or any generic type involving types + which will coerce.""" + logger.debug("Is %s unwanted?") + if type_ in TYPES_THAT_PYDANTIC_WILL_COERCE_TO: + logger.debug("yes") + return True + logger.debug("Maybe. Subargs are %s", get_args(type_)) + rv = any(field_type_unwanted(t) for t in get_args(type_)) + logger.debug("Conclusion: %s %s unwanted", type_, "is" if rv else "is not") + return rv + + +class PatchedBaseModel(PydanticBaseModel): + """A patched version of BaseModel that inspects fields after models are defined. + + We complain loudly if we see an unwanted type. + + Beware: ModelField.type_ is presumably private; this is likely to be very brittle. + """ + + @classmethod + def __init_subclass__(cls: Type[PydanticBaseModel], **kwargs: object): + for field in cls.__fields__.values(): + # Note that field.type_ and field.outer_type are computed based on the + # annotation type, see pydantic.fields.ModelField._type_analysis + if field_type_unwanted(field.outer_type_): + # TODO: this only reports the first bad field. Can we find all bad ones + # and report them all? + raise FieldHasUnwantedTypeException( + f"{cls.__module__}.{cls.__qualname__} has field '{field.name}' " + f"with unwanted type `{field.outer_type_}`" + ) + + +@contextmanager +def monkeypatch_pydantic() -> Generator[None, None, None]: + """Patch pydantic with our snooping versions of BaseModel and the con* functions. + + If the snooping functions see something they don't like, they'll raise a + ModelCheckingException instance. + """ + with contextlib.ExitStack() as patches: + # Most Synapse code ought to import the patched objects directly from + # `pydantic`. But we also patch their containing modules `pydantic.main` and + # `pydantic.types` for completeness. + patch_basemodel1 = unittest.mock.patch( + "pydantic.BaseModel", new=PatchedBaseModel + ) + patch_basemodel2 = unittest.mock.patch( + "pydantic.main.BaseModel", new=PatchedBaseModel + ) + patches.enter_context(patch_basemodel1) + patches.enter_context(patch_basemodel2) + for factory in CONSTRAINED_TYPE_FACTORIES_WITH_STRICT_FLAG: + wrapper: Callable = make_wrapper(factory) + patch1 = unittest.mock.patch(f"pydantic.{factory.__name__}", new=wrapper) + patch2 = unittest.mock.patch( + f"pydantic.types.{factory.__name__}", new=wrapper + ) + patches.enter_context(patch1) + patches.enter_context(patch2) + yield + + +def format_model_checker_exception(e: ModelCheckerException) -> str: + """Work out which line of code caused e. Format the line in a human-friendly way.""" + # TODO. FieldHasUnwantedTypeException gives better error messages. Can we ditch the + # patches of constr() etc, and instead inspect fields to look for ConstrainedStr + # with strict=False? There is some difficulty with the inheritance hierarchy + # because StrictStr < ConstrainedStr < str. + if isinstance(e, FieldHasUnwantedTypeException): + return e.message + elif isinstance(e, MissingStrictInConstrainedTypeException): + frame_summary = traceback.extract_tb(e.__traceback__)[-2] + return ( + f"Missing `strict=True` from {e.factory_name}() call \n" + + traceback.format_list([frame_summary])[0].lstrip() + ) + else: + raise ValueError(f"Unknown exception {e}") from e + + +def lint() -> int: + """Try to import all of Synapse and see if we spot any Pydantic type coercions. + + Print any problems, then return a status code suitable for sys.exit.""" + failures = do_lint() + if failures: + print(f"Found {len(failures)} problem(s)") + for failure in sorted(failures): + print(failure) + return os.EX_DATAERR if failures else os.EX_OK + + +def do_lint() -> Set[str]: + """Try to import all of Synapse and see if we spot any Pydantic type coercions.""" + failures = set() + + with monkeypatch_pydantic(): + logger.debug("Importing synapse") + try: + # TODO: make "synapse" an argument so we can target this script at + # a subpackage + module = importlib.import_module("synapse") + except ModelCheckerException as e: + logger.warning("Bad annotation found when importing synapse") + failures.add(format_model_checker_exception(e)) + return failures + + try: + logger.debug("Fetching subpackages") + module_infos = list( + pkgutil.walk_packages(module.__path__, f"{module.__name__}.") + ) + except ModelCheckerException as e: + logger.warning("Bad annotation found when looking for modules to import") + failures.add(format_model_checker_exception(e)) + return failures + + for module_info in module_infos: + logger.debug("Importing %s", module_info.name) + try: + importlib.import_module(module_info.name) + except ModelCheckerException as e: + logger.warning( + f"Bad annotation found when importing {module_info.name}" + ) + failures.add(format_model_checker_exception(e)) + + return failures + + +def run_test_snippet(source: str) -> None: + """Exec a snippet of source code in an isolated environment.""" + # To emulate `source` being called at the top level of the module, + # the globals and locals we provide apparently have to be the same mapping. + # + # > Remember that at the module level, globals and locals are the same dictionary. + # > If exec gets two separate objects as globals and locals, the code will be + # > executed as if it were embedded in a class definition. + globals_: Dict[str, object] + locals_: Dict[str, object] + globals_ = locals_ = {} + exec(textwrap.dedent(source), globals_, locals_) + + +class TestConstrainedTypesPatch(unittest.TestCase): + def test_expression_without_strict_raises(self) -> None: + with monkeypatch_pydantic(), self.assertRaises(ModelCheckerException): + run_test_snippet( + """ + from pydantic import constr + constr() + """ + ) + + def test_called_as_module_attribute_raises(self) -> None: + with monkeypatch_pydantic(), self.assertRaises(ModelCheckerException): + run_test_snippet( + """ + import pydantic + pydantic.constr() + """ + ) + + def test_wildcard_import_raises(self) -> None: + with monkeypatch_pydantic(), self.assertRaises(ModelCheckerException): + run_test_snippet( + """ + from pydantic import * + constr() + """ + ) + + def test_alternative_import_raises(self) -> None: + with monkeypatch_pydantic(), self.assertRaises(ModelCheckerException): + run_test_snippet( + """ + from pydantic.types import constr + constr() + """ + ) + + def test_alternative_import_attribute_raises(self) -> None: + with monkeypatch_pydantic(), self.assertRaises(ModelCheckerException): + run_test_snippet( + """ + import pydantic.types + pydantic.types.constr() + """ + ) + + def test_kwarg_but_no_strict_raises(self) -> None: + with monkeypatch_pydantic(), self.assertRaises(ModelCheckerException): + run_test_snippet( + """ + from pydantic import constr + constr(min_length=10) + """ + ) + + def test_kwarg_strict_False_raises(self) -> None: + with monkeypatch_pydantic(), self.assertRaises(ModelCheckerException): + run_test_snippet( + """ + from pydantic import constr + constr(strict=False) + """ + ) + + def test_kwarg_strict_True_doesnt_raise(self) -> None: + with monkeypatch_pydantic(): + run_test_snippet( + """ + from pydantic import constr + constr(strict=True) + """ + ) + + def test_annotation_without_strict_raises(self) -> None: + with monkeypatch_pydantic(), self.assertRaises(ModelCheckerException): + run_test_snippet( + """ + from pydantic import constr + x: constr() + """ + ) + + def test_field_annotation_without_strict_raises(self) -> None: + with monkeypatch_pydantic(), self.assertRaises(ModelCheckerException): + run_test_snippet( + """ + from pydantic import BaseModel, conint + class C: + x: conint() + """ + ) + + +class TestFieldTypeInspection(unittest.TestCase): + @parameterized.expand( + [ + ("str",), + ("bytes"), + ("int",), + ("float",), + ("bool"), + ("Optional[str]",), + ("Union[None, str]",), + ("List[str]",), + ("List[List[str]]",), + ("Dict[StrictStr, str]",), + ("Dict[str, StrictStr]",), + ("TypedDict('D', x=int)",), + ] + ) + def test_field_holding_unwanted_type_raises(self, annotation: str) -> None: + with monkeypatch_pydantic(), self.assertRaises(ModelCheckerException): + run_test_snippet( + f""" + from typing import * + from pydantic import * + class C(BaseModel): + f: {annotation} + """ + ) + + @parameterized.expand( + [ + ("StrictStr",), + ("StrictBytes"), + ("StrictInt",), + ("StrictFloat",), + ("StrictBool"), + ("constr(strict=True, min_length=10)",), + ("Optional[StrictStr]",), + ("Union[None, StrictStr]",), + ("List[StrictStr]",), + ("List[List[StrictStr]]",), + ("Dict[StrictStr, StrictStr]",), + ("TypedDict('D', x=StrictInt)",), + ] + ) + def test_field_holding_accepted_type_doesnt_raise(self, annotation: str) -> None: + with monkeypatch_pydantic(): + run_test_snippet( + f""" + from typing import * + from pydantic import * + class C(BaseModel): + f: {annotation} + """ + ) + + def test_field_holding_str_raises_with_alternative_import(self) -> None: + with monkeypatch_pydantic(), self.assertRaises(ModelCheckerException): + run_test_snippet( + """ + from pydantic.main import BaseModel + class C(BaseModel): + f: str + """ + ) + + +parser = argparse.ArgumentParser() +parser.add_argument("mode", choices=["lint", "test"], default="lint", nargs="?") +parser.add_argument("-v", "--verbose", action="store_true") + + +if __name__ == "__main__": + args = parser.parse_args(sys.argv[1:]) + logging.basicConfig( + format="%(asctime)s %(name)s:%(lineno)d %(levelname)s %(message)s", + level=logging.DEBUG if args.verbose else logging.INFO, + ) + # suppress logs we don't care about + logging.getLogger("xmlschema").setLevel(logging.WARNING) + if args.mode == "lint": + sys.exit(lint()) + elif args.mode == "test": + unittest.main(argv=sys.argv[:1]) diff --git a/scripts-dev/lint.sh b/scripts-dev/lint.sh index 377348b107..bf900645b1 100755 --- a/scripts-dev/lint.sh +++ b/scripts-dev/lint.sh @@ -106,4 +106,5 @@ isort "${files[@]}" python3 -m black "${files[@]}" ./scripts-dev/config-lint.sh flake8 "${files[@]}" +./scripts-dev/check_pydantic_models.py lint mypy diff --git a/synapse/api/auth.py b/synapse/api/auth.py index 523bad0c55..9a1aea083f 100644 --- a/synapse/api/auth.py +++ b/synapse/api/auth.py @@ -37,8 +37,7 @@ from synapse.logging.opentracing import ( start_active_span, trace, ) -from synapse.storage.databases.main.registration import TokenLookupResult -from synapse.types import Requester, UserID, create_requester +from synapse.types import Requester, create_requester if TYPE_CHECKING: from synapse.server import HomeServer @@ -70,14 +69,14 @@ class Auth: async def check_user_in_room( self, room_id: str, - user_id: str, + requester: Requester, allow_departed_users: bool = False, ) -> Tuple[str, Optional[str]]: """Check if the user is in the room, or was at some point. Args: room_id: The room to check. - user_id: The user to check. + requester: The user making the request, according to the access token. current_state: Optional map of the current state of the room. If provided then that map is used to check whether they are a @@ -94,6 +93,7 @@ class Auth: membership event ID of the user. """ + user_id = requester.user.to_string() ( membership, member_event_id, @@ -182,96 +182,69 @@ class Auth: access_token = self.get_access_token_from_request(request) - ( - user_id, - device_id, - app_service, - ) = await self._get_appservice_user_id_and_device_id(request) - if user_id and app_service: - if ip_addr and self._track_appservice_user_ips: - await self.store.insert_client_ip( - user_id=user_id, - access_token=access_token, - ip=ip_addr, - user_agent=user_agent, - device_id="dummy-device" - if device_id is None - else device_id, # stubbed - ) - - requester = create_requester( - user_id, app_service=app_service, device_id=device_id + # First check if it could be a request from an appservice + requester = await self._get_appservice_user(request) + if not requester: + # If not, it should be from a regular user + requester = await self.get_user_by_access_token( + access_token, allow_expired=allow_expired ) - request.requester = user_id - return requester - - user_info = await self.get_user_by_access_token( - access_token, allow_expired=allow_expired - ) - token_id = user_info.token_id - is_guest = user_info.is_guest - shadow_banned = user_info.shadow_banned - - # Deny the request if the user account has expired. - if not allow_expired: - if await self._account_validity_handler.is_user_expired( - user_info.user_id - ): - # Raise the error if either an account validity module has determined - # the account has expired, or the legacy account validity - # implementation is enabled and determined the account has expired - raise AuthError( - 403, - "User account has expired", - errcode=Codes.EXPIRED_ACCOUNT, - ) - - device_id = user_info.device_id - - if access_token and ip_addr: + # Deny the request if the user account has expired. + # This check is only done for regular users, not appservice ones. + if not allow_expired: + if await self._account_validity_handler.is_user_expired( + requester.user.to_string() + ): + # Raise the error if either an account validity module has determined + # the account has expired, or the legacy account validity + # implementation is enabled and determined the account has expired + raise AuthError( + 403, + "User account has expired", + errcode=Codes.EXPIRED_ACCOUNT, + ) + + if ip_addr and ( + not requester.app_service or self._track_appservice_user_ips + ): + # XXX(quenting): I'm 95% confident that we could skip setting the + # device_id to "dummy-device" for appservices, and that the only impact + # would be some rows which whould not deduplicate in the 'user_ips' + # table during the transition + recorded_device_id = ( + "dummy-device" + if requester.device_id is None and requester.app_service is not None + else requester.device_id + ) await self.store.insert_client_ip( - user_id=user_info.token_owner, + user_id=requester.authenticated_entity, access_token=access_token, ip=ip_addr, user_agent=user_agent, - device_id=device_id, + device_id=recorded_device_id, ) + # Track also the puppeted user client IP if enabled and the user is puppeting if ( - user_info.user_id != user_info.token_owner + requester.user.to_string() != requester.authenticated_entity and self._track_puppeted_user_ips ): await self.store.insert_client_ip( - user_id=user_info.user_id, + user_id=requester.user.to_string(), access_token=access_token, ip=ip_addr, user_agent=user_agent, - device_id=device_id, + device_id=requester.device_id, ) - if is_guest and not allow_guest: + if requester.is_guest and not allow_guest: raise AuthError( 403, "Guest access not allowed", errcode=Codes.GUEST_ACCESS_FORBIDDEN, ) - # Mark the token as used. This is used to invalidate old refresh - # tokens after some time. - if not user_info.token_used and token_id is not None: - await self.store.mark_access_token_as_used(token_id) - - requester = create_requester( - user_info.user_id, - token_id, - is_guest, - shadow_banned, - device_id, - app_service=app_service, - authenticated_entity=user_info.token_owner, - ) - request.requester = requester return requester except KeyError: @@ -308,9 +281,7 @@ class Auth: 403, "Application service has not registered this user (%s)" % user_id ) - async def _get_appservice_user_id_and_device_id( - self, request: Request - ) -> Tuple[Optional[str], Optional[str], Optional[ApplicationService]]: + async def _get_appservice_user(self, request: Request) -> Optional[Requester]: """ Given a request, reads the request parameters to determine: - whether it's an application service that's making this request @@ -325,15 +296,13 @@ class Auth: Must use `org.matrix.msc3202.device_id` in place of `device_id` for now. Returns: - 3-tuple of - (user ID?, device ID?, application service?) + the application service `Requester` of that request Postconditions: - - If an application service is returned, so is a user ID - - A user ID is never returned without an application service - - A device ID is never returned without a user ID or an application service - - The returned application service, if present, is permitted to control the - returned user ID. + - The `app_service` field in the returned `Requester` is set + - The `user_id` field in the returned `Requester` is either the application + service sender or the controlled user set by the `user_id` URI parameter + - The returned application service is permitted to control the returned user ID. - The returned device ID, if present, has been checked to be a valid device ID for the returned user ID. """ @@ -343,12 +312,12 @@ class Auth: self.get_access_token_from_request(request) ) if app_service is None: - return None, None, None + return None if app_service.ip_range_whitelist: ip_address = IPAddress(request.getClientAddress().host) if ip_address not in app_service.ip_range_whitelist: - return None, None, None + return None # This will always be set by the time Twisted calls us. assert request.args is not None @@ -382,13 +351,15 @@ class Auth: Codes.EXCLUSIVE, ) - return effective_user_id, effective_device_id, app_service + return create_requester( + effective_user_id, app_service=app_service, device_id=effective_device_id + ) async def get_user_by_access_token( self, token: str, allow_expired: bool = False, - ) -> TokenLookupResult: + ) -> Requester: """Validate access token and get user_id from it Args: @@ -405,9 +376,9 @@ class Auth: # First look in the database to see if the access token is present # as an opaque token. - r = await self.store.get_user_by_access_token(token) - if r: - valid_until_ms = r.valid_until_ms + user_info = await self.store.get_user_by_access_token(token) + if user_info: + valid_until_ms = user_info.valid_until_ms if ( not allow_expired and valid_until_ms is not None @@ -419,7 +390,20 @@ class Auth: msg="Access token has expired", soft_logout=True ) - return r + # Mark the token as used. This is used to invalidate old refresh + # tokens after some time. + await self.store.mark_access_token_as_used(user_info.token_id) + + requester = create_requester( + user_id=user_info.user_id, + access_token_id=user_info.token_id, + is_guest=user_info.is_guest, + shadow_banned=user_info.shadow_banned, + device_id=user_info.device_id, + authenticated_entity=user_info.token_owner, + ) + + return requester # If the token isn't found in the database, then it could still be a # macaroon for a guest, so we check that here. @@ -445,11 +429,12 @@ class Auth: "Guest access token used for regular user" ) - return TokenLookupResult( + return create_requester( user_id=user_id, is_guest=True, # all guests get the same device id device_id=GUEST_DEVICE_ID, + authenticated_entity=user_id, ) except ( pymacaroons.exceptions.MacaroonException, @@ -472,32 +457,33 @@ class Auth: request.requester = create_requester(service.sender, app_service=service) return service - async def is_server_admin(self, user: UserID) -> bool: + async def is_server_admin(self, requester: Requester) -> bool: """Check if the given user is a local server admin. Args: - user: user to check + requester: The user making the request, according to the access token. Returns: True if the user is an admin """ - return await self.store.is_server_admin(user) + return await self.store.is_server_admin(requester.user) - async def check_can_change_room_list(self, room_id: str, user: UserID) -> bool: + async def check_can_change_room_list( + self, room_id: str, requester: Requester + ) -> bool: """Determine whether the user is allowed to edit the room's entry in the published room list. Args: - room_id - user + room_id: The room to check. + requester: The user making the request, according to the access token. """ - is_admin = await self.is_server_admin(user) + is_admin = await self.is_server_admin(requester) if is_admin: return True - user_id = user.to_string() - await self.check_user_in_room(room_id, user_id) + await self.check_user_in_room(room_id, requester) # We currently require the user is a "moderator" in the room. We do this # by checking if they would (theoretically) be able to change the @@ -516,7 +502,9 @@ class Auth: send_level = event_auth.get_send_level( EventTypes.CanonicalAlias, "", power_level_event ) - user_level = event_auth.get_user_power_level(user_id, auth_events) + user_level = event_auth.get_user_power_level( + requester.user.to_string(), auth_events + ) return user_level >= send_level @@ -574,16 +562,16 @@ class Auth: @trace async def check_user_in_room_or_world_readable( - self, room_id: str, user_id: str, allow_departed_users: bool = False + self, room_id: str, requester: Requester, allow_departed_users: bool = False ) -> Tuple[str, Optional[str]]: """Checks that the user is or was in the room or the room is world readable. If it isn't then an exception is raised. Args: - room_id: room to check - user_id: user to check - allow_departed_users: if True, accept users that were previously - members but have now departed + room_id: The room to check. + requester: The user making the request, according to the access token. + allow_departed_users: If True, accept users that were previously + members but have now departed. Returns: Resolves to the current membership of the user in the room and the @@ -598,7 +586,7 @@ class Auth: # * The user is a guest user, and has joined the room # else it will throw. return await self.check_user_in_room( - room_id, user_id, allow_departed_users=allow_departed_users + room_id, requester, allow_departed_users=allow_departed_users ) except AuthError: visibility = await self._storage_controllers.state.get_current_state_event( @@ -613,6 +601,6 @@ class Auth: raise UnstableSpecAuthError( 403, "User %s not in room %s, and room previews are disabled" - % (user_id, room_id), + % (requester.user, room_id), errcode=Codes.NOT_JOINED, ) diff --git a/synapse/api/constants.py b/synapse/api/constants.py index 1d46fb0e43..c73aea622a 100644 --- a/synapse/api/constants.py +++ b/synapse/api/constants.py @@ -216,11 +216,11 @@ class EventContentFields: MSC2716_HISTORICAL: Final = "org.matrix.msc2716.historical" # For "insertion" events to indicate what the next batch ID should be in # order to connect to it - MSC2716_NEXT_BATCH_ID: Final = "org.matrix.msc2716.next_batch_id" + MSC2716_NEXT_BATCH_ID: Final = "next_batch_id" # Used on "batch" events to indicate which insertion event it connects to - MSC2716_BATCH_ID: Final = "org.matrix.msc2716.batch_id" + MSC2716_BATCH_ID: Final = "batch_id" # For "marker" events - MSC2716_MARKER_INSERTION: Final = "org.matrix.msc2716.marker.insertion" + MSC2716_INSERTION_EVENT_REFERENCE: Final = "insertion_event_reference" # The authorising user for joining a restricted room. AUTHORISING_USER: Final = "join_authorised_via_users_server" diff --git a/synapse/api/room_versions.py b/synapse/api/room_versions.py index 00e81b3afc..a0e4ab6db6 100644 --- a/synapse/api/room_versions.py +++ b/synapse/api/room_versions.py @@ -269,24 +269,6 @@ class RoomVersions: msc3787_knock_restricted_join_rule=False, msc3667_int_only_power_levels=False, ) - MSC2716v3 = RoomVersion( - "org.matrix.msc2716v3", - RoomDisposition.UNSTABLE, - EventFormatVersions.V3, - StateResolutionVersions.V2, - enforce_key_validity=True, - special_case_aliases_auth=False, - strict_canonicaljson=True, - limit_notifications_power_levels=True, - msc2176_redaction_rules=False, - msc3083_join_rules=False, - msc3375_redaction_rules=False, - msc2403_knocking=True, - msc2716_historical=True, - msc2716_redactions=True, - msc3787_knock_restricted_join_rule=False, - msc3667_int_only_power_levels=False, - ) MSC3787 = RoomVersion( "org.matrix.msc3787", RoomDisposition.UNSTABLE, @@ -323,6 +305,24 @@ class RoomVersions: msc3787_knock_restricted_join_rule=True, msc3667_int_only_power_levels=True, ) + MSC2716v4 = RoomVersion( + "org.matrix.msc2716v4", + RoomDisposition.UNSTABLE, + EventFormatVersions.V3, + StateResolutionVersions.V2, + enforce_key_validity=True, + special_case_aliases_auth=False, + strict_canonicaljson=True, + limit_notifications_power_levels=True, + msc2176_redaction_rules=False, + msc3083_join_rules=False, + msc3375_redaction_rules=False, + msc2403_knocking=True, + msc2716_historical=True, + msc2716_redactions=True, + msc3787_knock_restricted_join_rule=False, + msc3667_int_only_power_levels=False, + ) KNOWN_ROOM_VERSIONS: Dict[str, RoomVersion] = { @@ -338,9 +338,9 @@ KNOWN_ROOM_VERSIONS: Dict[str, RoomVersion] = { RoomVersions.V7, RoomVersions.V8, RoomVersions.V9, - RoomVersions.MSC2716v3, RoomVersions.MSC3787, RoomVersions.V10, + RoomVersions.MSC2716v4, ) } diff --git a/synapse/app/_base.py b/synapse/app/_base.py index 923891ae0d..4742435d3b 100644 --- a/synapse/app/_base.py +++ b/synapse/app/_base.py @@ -266,15 +266,48 @@ def register_start( reactor.callWhenRunning(lambda: defer.ensureDeferred(wrapper())) -def listen_metrics(bind_addresses: Iterable[str], port: int) -> None: +def listen_metrics( + bind_addresses: Iterable[str], port: int, enable_legacy_metric_names: bool +) -> None: """ Start Prometheus metrics server. """ - from synapse.metrics import RegistryProxy, start_http_server + from prometheus_client import start_http_server as start_http_server_prometheus + + from synapse.metrics import ( + RegistryProxy, + start_http_server as start_http_server_legacy, + ) for host in bind_addresses: logger.info("Starting metrics listener on %s:%d", host, port) - start_http_server(port, addr=host, registry=RegistryProxy) + if enable_legacy_metric_names: + start_http_server_legacy(port, addr=host, registry=RegistryProxy) + else: + _set_prometheus_client_use_created_metrics(False) + start_http_server_prometheus(port, addr=host, registry=RegistryProxy) + + +def _set_prometheus_client_use_created_metrics(new_value: bool) -> None: + """ + Sets whether prometheus_client should expose `_created`-suffixed metrics for + all gauges, histograms and summaries. + There is no programmatic way to disable this without poking at internals; + the proper way is to use an environment variable which prometheus_client + loads at import time. + + The motivation for disabling these `_created` metrics is that they're + a waste of space as they're not useful but they take up space in Prometheus. + """ + + import prometheus_client.metrics + + if hasattr(prometheus_client.metrics, "_use_created"): + prometheus_client.metrics._use_created = new_value + else: + logger.error( + "Can't disable `_created` metrics in prometheus_client (brittle hack broken?)" + ) def listen_manhole( diff --git a/synapse/app/generic_worker.py b/synapse/app/generic_worker.py index 42d1f6d219..5e3825fca6 100644 --- a/synapse/app/generic_worker.py +++ b/synapse/app/generic_worker.py @@ -412,7 +412,11 @@ class GenericWorkerServer(HomeServer): "enable_metrics is not True!" ) else: - _base.listen_metrics(listener.bind_addresses, listener.port) + _base.listen_metrics( + listener.bind_addresses, + listener.port, + enable_legacy_metric_names=self.config.metrics.enable_legacy_metrics, + ) else: logger.warning("Unsupported listener type: %s", listener.type) @@ -441,6 +445,13 @@ def start(config_options: List[str]) -> None: "synapse.app.user_dir", ) + if config.experimental.faster_joins_enabled: + raise ConfigError( + "You have enabled the experimental `faster_joins` config option, but it is " + "not compatible with worker deployments yet. Please disable `faster_joins` " + "or run Synapse as a single process deployment instead." + ) + synapse.events.USE_FROZEN_DICTS = config.server.use_frozen_dicts synapse.util.caches.TRACK_MEMORY_USAGE = config.caches.track_memory_usage diff --git a/synapse/app/homeserver.py b/synapse/app/homeserver.py index 745e704141..e57a926032 100644 --- a/synapse/app/homeserver.py +++ b/synapse/app/homeserver.py @@ -44,7 +44,6 @@ from synapse.app._base import ( register_start, ) from synapse.config._base import ConfigError, format_config_error -from synapse.config.emailconfig import ThreepidBehaviour from synapse.config.homeserver import HomeServerConfig from synapse.config.server import ListenerConfig from synapse.federation.transport.server import TransportLayerServer @@ -202,7 +201,7 @@ class SynapseHomeServer(HomeServer): } ) - if self.config.email.threepid_behaviour_email == ThreepidBehaviour.LOCAL: + if self.config.email.can_verify_email: from synapse.rest.synapse.client.password_reset import ( PasswordResetSubmitTokenResource, ) @@ -220,7 +219,10 @@ class SynapseHomeServer(HomeServer): resources.update({"/_matrix/consent": consent_resource}) if name == "federation": - resources.update({FEDERATION_PREFIX: TransportLayerServer(self)}) + federation_resource: Resource = TransportLayerServer(self) + if compress: + federation_resource = gz_wrap(federation_resource) + resources.update({FEDERATION_PREFIX: federation_resource}) if name == "openid": resources.update( @@ -305,7 +307,11 @@ class SynapseHomeServer(HomeServer): "enable_metrics is not True!" ) else: - _base.listen_metrics(listener.bind_addresses, listener.port) + _base.listen_metrics( + listener.bind_addresses, + listener.port, + enable_legacy_metric_names=self.config.metrics.enable_legacy_metrics, + ) else: # this shouldn't happen, as the listener type should have been checked # during parsing diff --git a/synapse/config/account_validity.py b/synapse/config/account_validity.py index d1335e77cd..b3972ede96 100644 --- a/synapse/config/account_validity.py +++ b/synapse/config/account_validity.py @@ -23,7 +23,7 @@ LEGACY_TEMPLATE_DIR_WARNING = """ This server's configuration file is using the deprecated 'template_dir' setting in the 'account_validity' section. Support for this setting has been deprecated and will be removed in a future version of Synapse. Server admins should instead use the new -'custom_templates_directory' setting documented here: +'custom_template_directory' setting documented here: https://matrix-org.github.io/synapse/latest/templates.html ---------------------------------------------------------------------------------------""" diff --git a/synapse/config/emailconfig.py b/synapse/config/emailconfig.py index 7765c5b454..a3af35b7c4 100644 --- a/synapse/config/emailconfig.py +++ b/synapse/config/emailconfig.py @@ -18,7 +18,6 @@ import email.utils import logging import os -from enum import Enum from typing import Any import attr @@ -53,7 +52,7 @@ LEGACY_TEMPLATE_DIR_WARNING = """ This server's configuration file is using the deprecated 'template_dir' setting in the 'email' section. Support for this setting has been deprecated and will be removed in a future version of Synapse. Server admins should instead use the new -'custom_templates_directory' setting documented here: +'custom_template_directory' setting documented here: https://matrix-org.github.io/synapse/latest/templates.html ---------------------------------------------------------------------------------------""" @@ -136,40 +135,22 @@ class EmailConfig(Config): self.email_enable_notifs = email_config.get("enable_notifs", False) - self.threepid_behaviour_email = ( - # Have Synapse handle the email sending if account_threepid_delegates.email - # is not defined - # msisdn is currently always remote while Synapse does not support any method of - # sending SMS messages - ThreepidBehaviour.REMOTE - if self.root.registration.account_threepid_delegate_email - else ThreepidBehaviour.LOCAL - ) - if config.get("trust_identity_server_for_password_resets"): raise ConfigError( - 'The config option "trust_identity_server_for_password_resets" has been removed.' - "Please consult the configuration manual at docs/usage/configuration/config_documentation.md for " - "details and update your config file." + 'The config option "trust_identity_server_for_password_resets" ' + "is no longer supported. Please remove it from the config file." ) - self.local_threepid_handling_disabled_due_to_email_config = False - if ( - self.threepid_behaviour_email == ThreepidBehaviour.LOCAL - and email_config == {} - ): - # We cannot warn the user this has happened here - # Instead do so when a user attempts to reset their password - self.local_threepid_handling_disabled_due_to_email_config = True - - self.threepid_behaviour_email = ThreepidBehaviour.OFF + # If we have email config settings, assume that we can verify ownership of + # email addresses. + self.can_verify_email = email_config != {} # Get lifetime of a validation token in milliseconds self.email_validation_token_lifetime = self.parse_duration( email_config.get("validation_token_lifetime", "1h") ) - if self.threepid_behaviour_email == ThreepidBehaviour.LOCAL: + if self.can_verify_email: missing = [] if not self.email_notif_from: missing.append("email.notif_from") @@ -360,18 +341,3 @@ class EmailConfig(Config): "Config option email.invite_client_location must be a http or https URL", path=("email", "invite_client_location"), ) - - -class ThreepidBehaviour(Enum): - """ - Enum to define the behaviour of Synapse with regards to when it contacts an identity - server for 3pid registration and password resets - - REMOTE = use an external server to send tokens - LOCAL = send tokens ourselves - OFF = disable registration via 3pid and password resets - """ - - REMOTE = "remote" - LOCAL = "local" - OFF = "off" diff --git a/synapse/config/experimental.py b/synapse/config/experimental.py index 7d17c958bb..c1ff417539 100644 --- a/synapse/config/experimental.py +++ b/synapse/config/experimental.py @@ -90,3 +90,6 @@ class ExperimentalConfig(Config): # MSC3848: Introduce errcodes for specific event sending failures self.msc3848_enabled: bool = experimental.get("msc3848_enabled", False) + + # MSC3852: Expose last seen user agent field on /_matrix/client/v3/devices. + self.msc3852_enabled: bool = experimental.get("msc3852_enabled", False) diff --git a/synapse/config/metrics.py b/synapse/config/metrics.py index 3b42be5b5b..f3134834e5 100644 --- a/synapse/config/metrics.py +++ b/synapse/config/metrics.py @@ -42,6 +42,35 @@ class MetricsConfig(Config): def read_config(self, config: JsonDict, **kwargs: Any) -> None: self.enable_metrics = config.get("enable_metrics", False) + + """ + ### `enable_legacy_metrics` (experimental) + + **Experimental: this option may be removed or have its behaviour + changed at any time, with no notice.** + + Set to `true` to publish both legacy and non-legacy Prometheus metric names, + or to `false` to only publish non-legacy Prometheus metric names. + Defaults to `true`. Has no effect if `enable_metrics` is `false`. + + Legacy metric names include: + - metrics containing colons in the name, such as `synapse_util_caches_response_cache:hits`, because colons are supposed to be reserved for user-defined recording rules; + - counters that don't end with the `_total` suffix, such as `synapse_federation_client_sent_edus`, therefore not adhering to the OpenMetrics standard. + + These legacy metric names are unconventional and not compliant with OpenMetrics standards. + They are included for backwards compatibility. + + Example configuration: + ```yaml + enable_legacy_metrics: false + ``` + + See https://github.com/matrix-org/synapse/issues/11106 for context. + + *Since v1.67.0.* + """ + self.enable_legacy_metrics = config.get("enable_legacy_metrics", True) + self.report_stats = config.get("report_stats", None) self.report_stats_endpoint = config.get( "report_stats_endpoint", "https://matrix.org/report-usage-stats/push" diff --git a/synapse/config/registration.py b/synapse/config/registration.py index 01fb0331bc..a888d976f2 100644 --- a/synapse/config/registration.py +++ b/synapse/config/registration.py @@ -13,7 +13,6 @@ # See the License for the specific language governing permissions and # limitations under the License. import argparse -import logging from typing import Any, Optional from synapse.api.constants import RoomCreationPreset @@ -21,15 +20,11 @@ from synapse.config._base import Config, ConfigError from synapse.types import JsonDict, RoomAlias, UserID from synapse.util.stringutils import random_string_with_symbols, strtobool -logger = logging.getLogger(__name__) - -LEGACY_EMAIL_DELEGATE_WARNING = """\ -Delegation of email verification to an identity server is now deprecated. To +NO_EMAIL_DELEGATE_ERROR = """\ +Delegation of email verification to an identity server is no longer supported. To continue to allow users to add email addresses to their accounts, and use them for password resets, configure Synapse with an SMTP server via the `email` setting, and remove `account_threepid_delegates.email`. - -This will be an error in a future version. """ @@ -64,9 +59,7 @@ class RegistrationConfig(Config): account_threepid_delegates = config.get("account_threepid_delegates") or {} if "email" in account_threepid_delegates: - logger.warning(LEGACY_EMAIL_DELEGATE_WARNING) - - self.account_threepid_delegate_email = account_threepid_delegates.get("email") + raise ConfigError(NO_EMAIL_DELEGATE_ERROR) self.account_threepid_delegate_msisdn = account_threepid_delegates.get("msisdn") self.default_identity_server = config.get("default_identity_server") self.allow_guest_access = config.get("allow_guest_access", False) diff --git a/synapse/config/sso.py b/synapse/config/sso.py index 2178cbf983..a452cc3a49 100644 --- a/synapse/config/sso.py +++ b/synapse/config/sso.py @@ -26,7 +26,7 @@ LEGACY_TEMPLATE_DIR_WARNING = """ This server's configuration file is using the deprecated 'template_dir' setting in the 'sso' section. Support for this setting has been deprecated and will be removed in a future version of Synapse. Server admins should instead use the new -'custom_templates_directory' setting documented here: +'custom_template_directory' setting documented here: https://matrix-org.github.io/synapse/latest/templates.html ---------------------------------------------------------------------------------------""" diff --git a/synapse/crypto/event_signing.py b/synapse/crypto/event_signing.py index 7520647d1e..23b799ac32 100644 --- a/synapse/crypto/event_signing.py +++ b/synapse/crypto/event_signing.py @@ -28,6 +28,7 @@ from synapse.api.errors import Codes, SynapseError from synapse.api.room_versions import RoomVersion from synapse.events import EventBase from synapse.events.utils import prune_event, prune_event_dict +from synapse.logging.opentracing import trace from synapse.types import JsonDict logger = logging.getLogger(__name__) @@ -35,6 +36,7 @@ logger = logging.getLogger(__name__) Hasher = Callable[[bytes], "hashlib._Hash"] +@trace def check_event_content_hash( event: EventBase, hash_algorithm: Hasher = hashlib.sha256 ) -> bool: diff --git a/synapse/events/spamcheck.py b/synapse/events/spamcheck.py index 4a3bfb38f1..623a2c71ea 100644 --- a/synapse/events/spamcheck.py +++ b/synapse/events/spamcheck.py @@ -32,6 +32,7 @@ from typing_extensions import Literal import synapse from synapse.api.errors import Codes +from synapse.logging.opentracing import trace from synapse.rest.media.v1._base import FileInfo from synapse.rest.media.v1.media_storage import ReadableFileWrapper from synapse.spam_checker_api import RegistrationBehaviour @@ -378,6 +379,7 @@ class SpamChecker: if check_media_file_for_spam is not None: self._check_media_file_for_spam_callbacks.append(check_media_file_for_spam) + @trace async def check_event_for_spam( self, event: "synapse.events.EventBase" ) -> Union[Tuple[Codes, JsonDict], str]: diff --git a/synapse/events/utils.py b/synapse/events/utils.py index ac91c5eb57..71853caad8 100644 --- a/synapse/events/utils.py +++ b/synapse/events/utils.py @@ -161,7 +161,7 @@ def prune_event_dict(room_version: RoomVersion, event_dict: JsonDict) -> JsonDic elif room_version.msc2716_redactions and event_type == EventTypes.MSC2716_BATCH: add_fields(EventContentFields.MSC2716_BATCH_ID) elif room_version.msc2716_redactions and event_type == EventTypes.MSC2716_MARKER: - add_fields(EventContentFields.MSC2716_MARKER_INSERTION) + add_fields(EventContentFields.MSC2716_INSERTION_EVENT_REFERENCE) allowed_fields = {k: v for k, v in event_dict.items() if k in allowed_keys} diff --git a/synapse/federation/federation_base.py b/synapse/federation/federation_base.py index 2522bf78fc..4269a98db2 100644 --- a/synapse/federation/federation_base.py +++ b/synapse/federation/federation_base.py @@ -23,6 +23,7 @@ from synapse.crypto.keyring import Keyring from synapse.events import EventBase, make_event_from_dict from synapse.events.utils import prune_event, validate_canonicaljson from synapse.http.servlet import assert_params_in_dict +from synapse.logging.opentracing import log_kv, trace from synapse.types import JsonDict, get_domain_from_id if TYPE_CHECKING: @@ -55,6 +56,7 @@ class FederationBase: self._clock = hs.get_clock() self._storage_controllers = hs.get_storage_controllers() + @trace async def _check_sigs_and_hash( self, room_version: RoomVersion, pdu: EventBase ) -> EventBase: @@ -97,17 +99,36 @@ class FederationBase: "Event %s seems to have been redacted; using our redacted copy", pdu.event_id, ) + log_kv( + { + "message": "Event seems to have been redacted; using our redacted copy", + "event_id": pdu.event_id, + } + ) else: logger.warning( "Event %s content has been tampered, redacting", pdu.event_id, ) + log_kv( + { + "message": "Event content has been tampered, redacting", + "event_id": pdu.event_id, + } + ) return redacted_event spam_check = await self.spam_checker.check_event_for_spam(pdu) if spam_check != self.spam_checker.NOT_SPAM: logger.warning("Event contains spam, soft-failing %s", pdu.event_id) + log_kv( + { + "message": "Event contains spam, redacting (to save disk space) " + "as well as soft-failing (to stop using the event in prev_events)", + "event_id": pdu.event_id, + } + ) # we redact (to save disk space) as well as soft-failing (to stop # using the event in prev_events). redacted_event = prune_event(pdu) @@ -117,6 +138,7 @@ class FederationBase: return pdu +@trace async def _check_sigs_on_pdu( keyring: Keyring, room_version: RoomVersion, pdu: EventBase ) -> None: diff --git a/synapse/federation/federation_client.py b/synapse/federation/federation_client.py index 54ffbd8170..7ee2974bb1 100644 --- a/synapse/federation/federation_client.py +++ b/synapse/federation/federation_client.py @@ -61,7 +61,7 @@ from synapse.federation.federation_base import ( ) from synapse.federation.transport.client import SendJoinResponse from synapse.http.types import QueryParams -from synapse.logging.opentracing import trace +from synapse.logging.opentracing import SynapseTags, log_kv, set_tag, tag_args, trace from synapse.types import JsonDict, UserID, get_domain_from_id from synapse.util.async_helpers import concurrently_execute from synapse.util.caches.expiringcache import ExpiringCache @@ -235,6 +235,7 @@ class FederationClient(FederationBase): ) @trace + @tag_args async def backfill( self, dest: str, room_id: str, limit: int, extremities: Collection[str] ) -> Optional[List[EventBase]]: @@ -337,6 +338,8 @@ class FederationClient(FederationBase): return None + @trace + @tag_args async def get_pdu( self, destinations: Iterable[str], @@ -448,6 +451,8 @@ class FederationClient(FederationBase): return event_copy + @trace + @tag_args async def get_room_state_ids( self, destination: str, room_id: str, event_id: str ) -> Tuple[List[str], List[str]]: @@ -467,6 +472,23 @@ class FederationClient(FederationBase): state_event_ids = result["pdu_ids"] auth_event_ids = result.get("auth_chain_ids", []) + set_tag( + SynapseTags.RESULT_PREFIX + "state_event_ids", + str(state_event_ids), + ) + set_tag( + SynapseTags.RESULT_PREFIX + "state_event_ids.length", + str(len(state_event_ids)), + ) + set_tag( + SynapseTags.RESULT_PREFIX + "auth_event_ids", + str(auth_event_ids), + ) + set_tag( + SynapseTags.RESULT_PREFIX + "auth_event_ids.length", + str(len(auth_event_ids)), + ) + if not isinstance(state_event_ids, list) or not isinstance( auth_event_ids, list ): @@ -474,6 +496,8 @@ class FederationClient(FederationBase): return state_event_ids, auth_event_ids + @trace + @tag_args async def get_room_state( self, destination: str, @@ -533,6 +557,7 @@ class FederationClient(FederationBase): return valid_state_events, valid_auth_events + @trace async def _check_sigs_and_hash_and_fetch( self, origin: str, @@ -562,11 +587,15 @@ class FederationClient(FederationBase): Returns: A list of PDUs that have valid signatures and hashes. """ + set_tag( + SynapseTags.RESULT_PREFIX + "pdus.length", + str(len(pdus)), + ) # We limit how many PDUs we check at once, as if we try to do hundreds # of thousands of PDUs at once we see large memory spikes. - valid_pdus = [] + valid_pdus: List[EventBase] = [] async def _execute(pdu: EventBase) -> None: valid_pdu = await self._check_sigs_and_hash_and_fetch_one( @@ -582,6 +611,8 @@ class FederationClient(FederationBase): return valid_pdus + @trace + @tag_args async def _check_sigs_and_hash_and_fetch_one( self, pdu: EventBase, @@ -614,16 +645,27 @@ class FederationClient(FederationBase): except InvalidEventSignatureError as e: logger.warning( "Signature on retrieved event %s was invalid (%s). " - "Checking local store/orgin server", + "Checking local store/origin server", pdu.event_id, e, ) + log_kv( + { + "message": "Signature on retrieved event was invalid. " + "Checking local store/origin server", + "event_id": pdu.event_id, + "InvalidEventSignatureError": e, + } + ) # Check local db. res = await self.store.get_event( pdu.event_id, allow_rejected=True, allow_none=True ) + # If the PDU fails its signature check and we don't have it in our + # database, we then request it from sender's server (if that is not the + # same as `origin`). pdu_origin = get_domain_from_id(pdu.sender) if not res and pdu_origin != origin: try: diff --git a/synapse/federation/federation_server.py b/synapse/federation/federation_server.py index db4b83a505..3bf84cf625 100644 --- a/synapse/federation/federation_server.py +++ b/synapse/federation/federation_server.py @@ -61,7 +61,12 @@ from synapse.logging.context import ( nested_logging_context, run_in_background, ) -from synapse.logging.opentracing import log_kv, start_active_span_from_edu, trace +from synapse.logging.opentracing import ( + log_kv, + start_active_span_from_edu, + tag_args, + trace, +) from synapse.metrics.background_process_metrics import wrap_as_background_process from synapse.replication.http.federation import ( ReplicationFederationSendEduRestServlet, @@ -547,6 +552,8 @@ class FederationServer(FederationBase): return 200, resp + @trace + @tag_args async def on_state_ids_request( self, origin: str, room_id: str, event_id: str ) -> Tuple[int, JsonDict]: @@ -569,6 +576,8 @@ class FederationServer(FederationBase): return 200, resp + @trace + @tag_args async def _on_state_ids_request_compute( self, room_id: str, event_id: str ) -> JsonDict: @@ -754,6 +763,17 @@ class FederationServer(FederationBase): The partial knock event. """ origin_host, _ = parse_server_name(origin) + + if await self.store.is_partial_state_room(room_id): + # Before we do anything: check if the room is partial-stated. + # Note that at the time this check was added, `on_make_knock_request` would + # block due to https://github.com/matrix-org/synapse/issues/12997. + raise SynapseError( + 404, + "Unable to handle /make_knock right now; this server is not fully joined.", + errcode=Codes.NOT_FOUND, + ) + await self.check_server_matches_acl(origin_host, room_id) room_version = await self.store.get_room_version(room_id) diff --git a/synapse/handlers/auth.py b/synapse/handlers/auth.py index bfa5535044..0327fc57a4 100644 --- a/synapse/handlers/auth.py +++ b/synapse/handlers/auth.py @@ -280,7 +280,7 @@ class AuthHandler: that it isn't stolen by re-authenticating them. Args: - requester: The user, as given by the access token + requester: The user making the request, according to the access token. request: The request sent by the client. @@ -1435,20 +1435,25 @@ class AuthHandler: access_token: access token to be deleted """ - user_info = await self.auth.get_user_by_access_token(access_token) + token = await self.store.get_user_by_access_token(access_token) + if not token: + # At this point, the token should already have been fetched once by + # the caller, so this should not happen, unless of a race condition + # between two delete requests + raise SynapseError(HTTPStatus.UNAUTHORIZED, "Unrecognised access token") await self.store.delete_access_token(access_token) # see if any modules want to know about this await self.password_auth_provider.on_logged_out( - user_id=user_info.user_id, - device_id=user_info.device_id, + user_id=token.user_id, + device_id=token.device_id, access_token=access_token, ) # delete pushers associated with this access token - if user_info.token_id is not None: + if token.token_id is not None: await self.hs.get_pusherpool().remove_pushers_by_access_token( - user_info.user_id, (user_info.token_id,) + token.user_id, (token.token_id,) ) async def delete_access_tokens_for_user( diff --git a/synapse/handlers/device.py b/synapse/handlers/device.py index 1a8379854c..9c2c3a0e68 100644 --- a/synapse/handlers/device.py +++ b/synapse/handlers/device.py @@ -74,6 +74,7 @@ class DeviceWorkerHandler: self._state_storage = hs.get_storage_controllers().state self._auth_handler = hs.get_auth_handler() self.server_name = hs.hostname + self._msc3852_enabled = hs.config.experimental.msc3852_enabled @trace async def get_devices_by_user(self, user_id: str) -> List[JsonDict]: @@ -309,6 +310,7 @@ class DeviceHandler(DeviceWorkerHandler): super().__init__(hs) self.federation_sender = hs.get_federation_sender() + self._storage_controllers = hs.get_storage_controllers() self.device_list_updater = DeviceListUpdater(hs, self) @@ -693,8 +695,11 @@ class DeviceHandler(DeviceWorkerHandler): # Ignore any users that aren't ours if self.hs.is_mine_id(user_id): - joined_user_ids = await self.store.get_users_in_room(room_id) - hosts = {get_domain_from_id(u) for u in joined_user_ids} + hosts = set( + await self._storage_controllers.state.get_current_hosts_in_room( + room_id + ) + ) hosts.discard(self.server_name) # Check if we've already sent this update to some hosts @@ -747,7 +752,13 @@ def _update_device_from_client_ips( device: JsonDict, client_ips: Mapping[Tuple[str, str], Mapping[str, Any]] ) -> None: ip = client_ips.get((device["user_id"], device["device_id"]), {}) - device.update({"last_seen_ts": ip.get("last_seen"), "last_seen_ip": ip.get("ip")}) + device.update( + { + "last_seen_user_agent": ip.get("user_agent"), + "last_seen_ts": ip.get("last_seen"), + "last_seen_ip": ip.get("ip"), + } + ) class DeviceListUpdater: diff --git a/synapse/handlers/directory.py b/synapse/handlers/directory.py index 09a7a4b238..7127d5aefc 100644 --- a/synapse/handlers/directory.py +++ b/synapse/handlers/directory.py @@ -30,7 +30,7 @@ from synapse.api.errors import ( from synapse.appservice import ApplicationService from synapse.module_api import NOT_SPAM from synapse.storage.databases.main.directory import RoomAliasMapping -from synapse.types import JsonDict, Requester, RoomAlias, UserID, get_domain_from_id +from synapse.types import JsonDict, Requester, RoomAlias if TYPE_CHECKING: from synapse.server import HomeServer @@ -83,8 +83,9 @@ class DirectoryHandler: # TODO(erikj): Add transactions. # TODO(erikj): Check if there is a current association. if not servers: - users = await self.store.get_users_in_room(room_id) - servers = {get_domain_from_id(u) for u in users} + servers = await self._storage_controllers.state.get_current_hosts_in_room( + room_id + ) if not servers: raise SynapseError(400, "Failed to get server list") @@ -133,7 +134,7 @@ class DirectoryHandler: else: # Server admins are not subject to the same constraints as normal # users when creating an alias (e.g. being in the room). - is_admin = await self.auth.is_server_admin(requester.user) + is_admin = await self.auth.is_server_admin(requester) if (self.require_membership and check_membership) and not is_admin: rooms_for_user = await self.store.get_rooms_for_user(user_id) @@ -197,7 +198,7 @@ class DirectoryHandler: user_id = requester.user.to_string() try: - can_delete = await self._user_can_delete_alias(room_alias, user_id) + can_delete = await self._user_can_delete_alias(room_alias, requester) except StoreError as e: if e.code == 404: raise NotFoundError("Unknown room alias") @@ -287,8 +288,9 @@ class DirectoryHandler: Codes.NOT_FOUND, ) - users = await self.store.get_users_in_room(room_id) - extra_servers = {get_domain_from_id(u) for u in users} + extra_servers = await self._storage_controllers.state.get_current_hosts_in_room( + room_id + ) servers_set = set(extra_servers) | set(servers) # If this server is in the list of servers, return it first. @@ -400,7 +402,9 @@ class DirectoryHandler: # either no interested services, or no service with an exclusive lock return True - async def _user_can_delete_alias(self, alias: RoomAlias, user_id: str) -> bool: + async def _user_can_delete_alias( + self, alias: RoomAlias, requester: Requester + ) -> bool: """Determine whether a user can delete an alias. One of the following must be true: @@ -413,7 +417,7 @@ class DirectoryHandler: """ creator = await self.store.get_room_alias_creator(alias.to_string()) - if creator == user_id: + if creator == requester.user.to_string(): return True # Resolve the alias to the corresponding room. @@ -422,9 +426,7 @@ class DirectoryHandler: if not room_id: return False - return await self.auth.check_can_change_room_list( - room_id, UserID.from_string(user_id) - ) + return await self.auth.check_can_change_room_list(room_id, requester) async def edit_published_room_list( self, requester: Requester, room_id: str, visibility: str @@ -463,7 +465,7 @@ class DirectoryHandler: raise SynapseError(400, "Unknown room") can_change_room_list = await self.auth.check_can_change_room_list( - room_id, requester.user + room_id, requester ) if not can_change_room_list: raise AuthError( @@ -528,10 +530,8 @@ class DirectoryHandler: Get a list of the aliases that currently point to this room on this server """ # allow access to server admins and current members of the room - is_admin = await self.auth.is_server_admin(requester.user) + is_admin = await self.auth.is_server_admin(requester) if not is_admin: - await self.auth.check_user_in_room_or_world_readable( - room_id, requester.user.to_string() - ) + await self.auth.check_user_in_room_or_world_readable(room_id, requester) return await self.store.get_aliases_for_room(room_id) diff --git a/synapse/handlers/event_auth.py b/synapse/handlers/event_auth.py index a2dd9c7efa..c3ddc5d182 100644 --- a/synapse/handlers/event_auth.py +++ b/synapse/handlers/event_auth.py @@ -129,12 +129,9 @@ class EventAuthHandler: else: users = {} - # Find the user with the highest power level. - users_in_room = await self._store.get_users_in_room(room_id) - # Only interested in local users. - local_users_in_room = [ - u for u in users_in_room if get_domain_from_id(u) == self._server_name - ] + # Find the user with the highest power level (only interested in local + # users). + local_users_in_room = await self._store.get_local_users_in_room(room_id) chosen_user = max( local_users_in_room, key=lambda user: users.get(user, users_default_level), diff --git a/synapse/handlers/events.py b/synapse/handlers/events.py index ac13340d3a..949b69cb41 100644 --- a/synapse/handlers/events.py +++ b/synapse/handlers/events.py @@ -151,7 +151,7 @@ class EventHandler: """Retrieve a single specified event. Args: - user: The user requesting the event + user: The local user requesting the event room_id: The expected room id. We'll return None if the event's room does not match. event_id: The event ID to obtain. @@ -173,8 +173,11 @@ class EventHandler: if not event: return None - users = await self.store.get_users_in_room(event.room_id) - is_peeking = user.to_string() not in users + is_user_in_room = await self.store.check_local_user_in_room( + user_id=user.to_string(), room_id=event.room_id + ) + # The user is peeking if they aren't in the room already + is_peeking = not is_user_in_room filtered = await filter_events_for_client( self._storage_controllers, user.to_string(), [event], is_peeking=is_peeking diff --git a/synapse/handlers/federation.py b/synapse/handlers/federation.py index 5042236742..e151962055 100644 --- a/synapse/handlers/federation.py +++ b/synapse/handlers/federation.py @@ -32,6 +32,7 @@ from typing import ( ) import attr +from prometheus_client import Histogram from signedjson.key import decode_verify_key_bytes from signedjson.sign import verify_signed_json from unpaddedbase64 import decode_base64 @@ -59,7 +60,7 @@ from synapse.events.validator import EventValidator from synapse.federation.federation_client import InvalidResponseError from synapse.http.servlet import assert_params_in_dict from synapse.logging.context import nested_logging_context -from synapse.logging.opentracing import trace +from synapse.logging.opentracing import SynapseTags, set_tag, tag_args, trace from synapse.metrics.background_process_metrics import run_as_background_process from synapse.module_api import NOT_SPAM from synapse.replication.http.federation import ( @@ -79,6 +80,29 @@ if TYPE_CHECKING: logger = logging.getLogger(__name__) +# Added to debug performance and track progress on optimizations +backfill_processing_before_timer = Histogram( + "synapse_federation_backfill_processing_before_time_seconds", + "sec", + [], + buckets=( + 0.1, + 0.5, + 1.0, + 2.5, + 5.0, + 7.5, + 10.0, + 15.0, + 20.0, + 30.0, + 40.0, + 60.0, + 80.0, + "+Inf", + ), +) + def get_domains_from_state(state: StateMap[EventBase]) -> List[Tuple[str, int]]: """Get joined domains from state @@ -138,6 +162,7 @@ class FederationHandler: def __init__(self, hs: "HomeServer"): self.hs = hs + self.clock = hs.get_clock() self.store = hs.get_datastores().main self._storage_controllers = hs.get_storage_controllers() self._state_storage_controller = self._storage_controllers.state @@ -197,12 +222,39 @@ class FederationHandler: return. This is used as part of the heuristic to decide if we should back paginate. """ + # Starting the processing time here so we can include the room backfill + # linearizer lock queue in the timing + processing_start_time = self.clock.time_msec() + async with self._room_backfill.queue(room_id): - return await self._maybe_backfill_inner(room_id, current_depth, limit) + return await self._maybe_backfill_inner( + room_id, + current_depth, + limit, + processing_start_time=processing_start_time, + ) async def _maybe_backfill_inner( - self, room_id: str, current_depth: int, limit: int + self, + room_id: str, + current_depth: int, + limit: int, + *, + processing_start_time: int, ) -> bool: + """ + Checks whether the `current_depth` is at or approaching any backfill + points in the room and if so, will backfill. We only care about + checking backfill points that happened before the `current_depth` + (meaning less than or equal to the `current_depth`). + + Args: + room_id: The room to backfill in. + current_depth: The depth to check at for any upcoming backfill points. + limit: The max number of events to request from the remote federated server. + processing_start_time: The time when `maybe_backfill` started + processing. Only used for timing. + """ backwards_extremities = [ _BackfillPoint(event_id, depth, _BackfillPointType.BACKWARDS_EXTREMITY) for event_id, depth in await self.store.get_oldest_event_ids_with_depth_in_room( @@ -370,6 +422,14 @@ class FederationHandler: logger.debug( "_maybe_backfill_inner: extremities_to_request %s", extremities_to_request ) + set_tag( + SynapseTags.RESULT_PREFIX + "extremities_to_request", + str(extremities_to_request), + ) + set_tag( + SynapseTags.RESULT_PREFIX + "extremities_to_request.length", + str(len(extremities_to_request)), + ) # Now we need to decide which hosts to hit first. @@ -425,6 +485,11 @@ class FederationHandler: return False + processing_end_time = self.clock.time_msec() + backfill_processing_before_timer.observe( + (processing_end_time - processing_start_time) / 1000 + ) + success = await try_backfill(likely_domains) if success: return True @@ -1081,6 +1146,8 @@ class FederationHandler: return event + @trace + @tag_args async def get_state_ids_for_pdu(self, room_id: str, event_id: str) -> List[str]: """Returns the state at the event. i.e. not including said event.""" event = await self.store.get_event(event_id, check_room_id=room_id) diff --git a/synapse/handlers/federation_event.py b/synapse/handlers/federation_event.py index 8968b705d4..048c4111f6 100644 --- a/synapse/handlers/federation_event.py +++ b/synapse/handlers/federation_event.py @@ -29,7 +29,7 @@ from typing import ( Tuple, ) -from prometheus_client import Counter +from prometheus_client import Counter, Histogram from synapse import event_auth from synapse.api.constants import ( @@ -59,7 +59,13 @@ from synapse.events import EventBase from synapse.events.snapshot import EventContext from synapse.federation.federation_client import InvalidResponseError from synapse.logging.context import nested_logging_context -from synapse.logging.opentracing import trace +from synapse.logging.opentracing import ( + SynapseTags, + set_tag, + start_active_span, + tag_args, + trace, +) from synapse.metrics.background_process_metrics import run_as_background_process from synapse.replication.http.devices import ReplicationUserDevicesResyncRestServlet from synapse.replication.http.federation import ( @@ -92,6 +98,36 @@ soft_failed_event_counter = Counter( "Events received over federation that we marked as soft_failed", ) +# Added to debug performance and track progress on optimizations +backfill_processing_after_timer = Histogram( + "synapse_federation_backfill_processing_after_time_seconds", + "sec", + [], + buckets=( + 0.1, + 0.25, + 0.5, + 1.0, + 2.5, + 5.0, + 7.5, + 10.0, + 15.0, + 20.0, + 25.0, + 30.0, + 40.0, + 50.0, + 60.0, + 80.0, + 100.0, + 120.0, + 150.0, + 180.0, + "+Inf", + ), +) + class FederationEventHandler: """Handles events that originated from federation. @@ -410,6 +446,7 @@ class FederationEventHandler: prev_member_event, ) + @trace async def process_remote_join( self, origin: str, @@ -597,20 +634,21 @@ class FederationEventHandler: if not events: return - # if there are any events in the wrong room, the remote server is buggy and - # should not be trusted. - for ev in events: - if ev.room_id != room_id: - raise InvalidResponseError( - f"Remote server {dest} returned event {ev.event_id} which is in " - f"room {ev.room_id}, when we were backfilling in {room_id}" - ) + with backfill_processing_after_timer.time(): + # if there are any events in the wrong room, the remote server is buggy and + # should not be trusted. + for ev in events: + if ev.room_id != room_id: + raise InvalidResponseError( + f"Remote server {dest} returned event {ev.event_id} which is in " + f"room {ev.room_id}, when we were backfilling in {room_id}" + ) - await self._process_pulled_events( - dest, - events, - backfilled=True, - ) + await self._process_pulled_events( + dest, + events, + backfilled=True, + ) @trace async def _get_missing_events_for_pdu( @@ -715,7 +753,7 @@ class FederationEventHandler: @trace async def _process_pulled_events( - self, origin: str, events: Iterable[EventBase], backfilled: bool + self, origin: str, events: Collection[EventBase], backfilled: bool ) -> None: """Process a batch of events we have pulled from a remote server @@ -730,6 +768,15 @@ class FederationEventHandler: backfilled: True if this is part of a historical batch of events (inhibits notification to clients, and validation of device keys.) """ + set_tag( + SynapseTags.FUNC_ARG_PREFIX + "event_ids", + str([event.event_id for event in events]), + ) + set_tag( + SynapseTags.FUNC_ARG_PREFIX + "event_ids.length", + str(len(events)), + ) + set_tag(SynapseTags.FUNC_ARG_PREFIX + "backfilled", str(backfilled)) logger.debug( "processing pulled backfilled=%s events=%s", backfilled, @@ -753,6 +800,7 @@ class FederationEventHandler: await self._process_pulled_event(origin, ev, backfilled=backfilled) @trace + @tag_args async def _process_pulled_event( self, origin: str, event: EventBase, backfilled: bool ) -> None: @@ -854,6 +902,7 @@ class FederationEventHandler: else: raise + @trace async def _compute_event_context_with_maybe_missing_prevs( self, dest: str, event: EventBase ) -> EventContext: @@ -970,6 +1019,8 @@ class FederationEventHandler: event, state_ids_before_event=state_map, partial_state=partial_state ) + @trace + @tag_args async def _get_state_ids_after_missing_prev_event( self, destination: str, @@ -1009,10 +1060,10 @@ class FederationEventHandler: logger.debug("Fetching %i events from cache/store", len(desired_events)) have_events = await self._store.have_seen_events(room_id, desired_events) - missing_desired_events = desired_events - have_events + missing_desired_event_ids = desired_events - have_events logger.debug( "We are missing %i events (got %i)", - len(missing_desired_events), + len(missing_desired_event_ids), len(have_events), ) @@ -1024,13 +1075,30 @@ class FederationEventHandler: # already have a bunch of the state events. It would be nice if the # federation api gave us a way of finding out which we actually need. - missing_auth_events = set(auth_event_ids) - have_events - missing_auth_events.difference_update( - await self._store.have_seen_events(room_id, missing_auth_events) + missing_auth_event_ids = set(auth_event_ids) - have_events + missing_auth_event_ids.difference_update( + await self._store.have_seen_events(room_id, missing_auth_event_ids) ) - logger.debug("We are also missing %i auth events", len(missing_auth_events)) + logger.debug("We are also missing %i auth events", len(missing_auth_event_ids)) - missing_events = missing_desired_events | missing_auth_events + missing_event_ids = missing_desired_event_ids | missing_auth_event_ids + + set_tag( + SynapseTags.RESULT_PREFIX + "missing_auth_event_ids", + str(missing_auth_event_ids), + ) + set_tag( + SynapseTags.RESULT_PREFIX + "missing_auth_event_ids.length", + str(len(missing_auth_event_ids)), + ) + set_tag( + SynapseTags.RESULT_PREFIX + "missing_desired_event_ids", + str(missing_desired_event_ids), + ) + set_tag( + SynapseTags.RESULT_PREFIX + "missing_desired_event_ids.length", + str(len(missing_desired_event_ids)), + ) # Making an individual request for each of 1000s of events has a lot of # overhead. On the other hand, we don't really want to fetch all of the events @@ -1041,13 +1109,13 @@ class FederationEventHandler: # # TODO: might it be better to have an API which lets us do an aggregate event # request - if (len(missing_events) * 10) >= len(auth_event_ids) + len(state_event_ids): + if (len(missing_event_ids) * 10) >= len(auth_event_ids) + len(state_event_ids): logger.debug("Requesting complete state from remote") await self._get_state_and_persist(destination, room_id, event_id) else: - logger.debug("Fetching %i events from remote", len(missing_events)) + logger.debug("Fetching %i events from remote", len(missing_event_ids)) await self._get_events_and_persist( - destination=destination, room_id=room_id, event_ids=missing_events + destination=destination, room_id=room_id, event_ids=missing_event_ids ) # We now need to fill out the state map, which involves fetching the @@ -1104,6 +1172,14 @@ class FederationEventHandler: event_id, failed_to_fetch, ) + set_tag( + SynapseTags.RESULT_PREFIX + "failed_to_fetch", + str(failed_to_fetch), + ) + set_tag( + SynapseTags.RESULT_PREFIX + "failed_to_fetch.length", + str(len(failed_to_fetch)), + ) if remote_event.is_state() and remote_event.rejected_reason is None: state_map[ @@ -1112,6 +1188,8 @@ class FederationEventHandler: return state_map + @trace + @tag_args async def _get_state_and_persist( self, destination: str, room_id: str, event_id: str ) -> None: @@ -1133,6 +1211,7 @@ class FederationEventHandler: destination=destination, room_id=room_id, event_ids=(event_id,) ) + @trace async def _process_received_pdu( self, origin: str, @@ -1283,6 +1362,7 @@ class FederationEventHandler: except Exception: logger.exception("Failed to resync device for %s", sender) + @trace async def _handle_marker_event(self, origin: str, marker_event: EventBase) -> None: """Handles backfilling the insertion event when we receive a marker event that points to one. @@ -1314,7 +1394,7 @@ class FederationEventHandler: logger.debug("_handle_marker_event: received %s", marker_event) insertion_event_id = marker_event.content.get( - EventContentFields.MSC2716_MARKER_INSERTION + EventContentFields.MSC2716_INSERTION_EVENT_REFERENCE ) if insertion_event_id is None: @@ -1414,6 +1494,8 @@ class FederationEventHandler: return event_from_response + @trace + @tag_args async def _get_events_and_persist( self, destination: str, room_id: str, event_ids: Collection[str] ) -> None: @@ -1459,6 +1541,7 @@ class FederationEventHandler: logger.info("Fetched %i events of %i requested", len(events), len(event_ids)) await self._auth_and_persist_outliers(room_id, events) + @trace async def _auth_and_persist_outliers( self, room_id: str, events: Iterable[EventBase] ) -> None: @@ -1477,6 +1560,16 @@ class FederationEventHandler: """ event_map = {event.event_id: event for event in events} + event_ids = event_map.keys() + set_tag( + SynapseTags.FUNC_ARG_PREFIX + "event_ids", + str(event_ids), + ) + set_tag( + SynapseTags.FUNC_ARG_PREFIX + "event_ids.length", + str(len(event_ids)), + ) + # filter out any events we have already seen. This might happen because # the events were eagerly pushed to us (eg, during a room join), or because # another thread has raced against us since we decided to request the event. @@ -1593,6 +1686,7 @@ class FederationEventHandler: backfilled=True, ) + @trace async def _check_event_auth( self, origin: Optional[str], event: EventBase, context: EventContext ) -> None: @@ -1631,6 +1725,14 @@ class FederationEventHandler: claimed_auth_events = await self._load_or_fetch_auth_events_for_event( origin, event ) + set_tag( + SynapseTags.RESULT_PREFIX + "claimed_auth_events", + str([ev.event_id for ev in claimed_auth_events]), + ) + set_tag( + SynapseTags.RESULT_PREFIX + "claimed_auth_events.length", + str(len(claimed_auth_events)), + ) # ... and check that the event passes auth at those auth events. # https://spec.matrix.org/v1.3/server-server-api/#checks-performed-on-receipt-of-a-pdu: @@ -1728,6 +1830,7 @@ class FederationEventHandler: ) context.rejected = RejectedReason.AUTH_ERROR + @trace async def _maybe_kick_guest_users(self, event: EventBase) -> None: if event.type != EventTypes.GuestAccess: return @@ -1935,6 +2038,8 @@ class FederationEventHandler: # instead we raise an AuthError, which will make the caller ignore it. raise AuthError(code=HTTPStatus.FORBIDDEN, msg="Auth events could not be found") + @trace + @tag_args async def _get_remote_auth_chain_for_event( self, destination: str, room_id: str, event_id: str ) -> None: @@ -1963,6 +2068,7 @@ class FederationEventHandler: await self._auth_and_persist_outliers(room_id, remote_auth_events) + @trace async def _run_push_actions_and_persist_event( self, event: EventBase, context: EventContext, backfilled: bool = False ) -> None: @@ -2071,8 +2177,17 @@ class FederationEventHandler: self._message_handler.maybe_schedule_expiry(event) if not backfilled: # Never notify for backfilled events - for event in events: - await self._notify_persisted_event(event, max_stream_token) + with start_active_span("notify_persisted_events"): + set_tag( + SynapseTags.RESULT_PREFIX + "event_ids", + str([ev.event_id for ev in events]), + ) + set_tag( + SynapseTags.RESULT_PREFIX + "event_ids.length", + str(len(events)), + ) + for event in events: + await self._notify_persisted_event(event, max_stream_token) return max_stream_token.stream diff --git a/synapse/handlers/identity.py b/synapse/handlers/identity.py index e5afe84df9..9571d461c8 100644 --- a/synapse/handlers/identity.py +++ b/synapse/handlers/identity.py @@ -26,7 +26,6 @@ from synapse.api.errors import ( SynapseError, ) from synapse.api.ratelimiting import Ratelimiter -from synapse.config.emailconfig import ThreepidBehaviour from synapse.http import RequestTimedOutError from synapse.http.client import SimpleHttpClient from synapse.http.site import SynapseRequest @@ -416,48 +415,6 @@ class IdentityHandler: return session_id - async def request_email_token( - self, - id_server: str, - email: str, - client_secret: str, - send_attempt: int, - next_link: Optional[str] = None, - ) -> JsonDict: - """ - Request an external server send an email on our behalf for the purposes of threepid - validation. - - Args: - id_server: The identity server to proxy to - email: The email to send the message to - client_secret: The unique client_secret sends by the user - send_attempt: Which attempt this is - next_link: A link to redirect the user to once they submit the token - - Returns: - The json response body from the server - """ - params = { - "email": email, - "client_secret": client_secret, - "send_attempt": send_attempt, - } - if next_link: - params["next_link"] = next_link - - try: - data = await self.http_client.post_json_get_json( - id_server + "/_matrix/identity/api/v1/validate/email/requestToken", - params, - ) - return data - except HttpResponseException as e: - logger.info("Proxied requestToken failed: %r", e) - raise e.to_synapse_error() - except RequestTimedOutError: - raise SynapseError(500, "Timed out contacting identity server") - async def requestMsisdnToken( self, id_server: str, @@ -531,18 +488,7 @@ class IdentityHandler: validation_session = None # Try to validate as email - if self.hs.config.email.threepid_behaviour_email == ThreepidBehaviour.REMOTE: - # Remote emails will only be used if a valid identity server is provided. - assert ( - self.hs.config.registration.account_threepid_delegate_email is not None - ) - - # Ask our delegated email identity server - validation_session = await self.threepid_from_creds( - self.hs.config.registration.account_threepid_delegate_email, - threepid_creds, - ) - elif self.hs.config.email.threepid_behaviour_email == ThreepidBehaviour.LOCAL: + if self.hs.config.email.can_verify_email: # Get a validated session matching these details validation_session = await self.store.get_threepid_validation_session( "email", client_secret, sid=sid, validated=True diff --git a/synapse/handlers/initial_sync.py b/synapse/handlers/initial_sync.py index 6484e47e5f..860c82c110 100644 --- a/synapse/handlers/initial_sync.py +++ b/synapse/handlers/initial_sync.py @@ -309,18 +309,18 @@ class InitialSyncHandler: if blocked: raise SynapseError(403, "This room has been blocked on this server") - user_id = requester.user.to_string() - ( membership, member_event_id, ) = await self.auth.check_user_in_room_or_world_readable( room_id, - user_id, + requester, allow_departed_users=True, ) is_peeking = member_event_id is None + user_id = requester.user.to_string() + if membership == Membership.JOIN: result = await self._room_initial_sync_joined( user_id, room_id, pagin_config, membership, is_peeking diff --git a/synapse/handlers/message.py b/synapse/handlers/message.py index d77f2c2fb6..ec7c73a758 100644 --- a/synapse/handlers/message.py +++ b/synapse/handlers/message.py @@ -104,7 +104,7 @@ class MessageHandler: async def get_room_data( self, - user_id: str, + requester: Requester, room_id: str, event_type: str, state_key: str, @@ -112,7 +112,7 @@ class MessageHandler: """Get data from a room. Args: - user_id + requester: The user who did the request. room_id event_type state_key @@ -125,7 +125,7 @@ class MessageHandler: membership, membership_event_id, ) = await self.auth.check_user_in_room_or_world_readable( - room_id, user_id, allow_departed_users=True + room_id, requester, allow_departed_users=True ) if membership == Membership.JOIN: @@ -161,11 +161,10 @@ class MessageHandler: async def get_state_events( self, - user_id: str, + requester: Requester, room_id: str, state_filter: Optional[StateFilter] = None, at_token: Optional[StreamToken] = None, - is_guest: bool = False, ) -> List[dict]: """Retrieve all state events for a given room. If the user is joined to the room then return the current state. If the user has @@ -174,14 +173,13 @@ class MessageHandler: visible. Args: - user_id: The user requesting state events. + requester: The user requesting state events. room_id: The room ID to get all state events from. state_filter: The state filter used to fetch state from the database. at_token: the stream token of the at which we are requesting the stats. If the user is not allowed to view the state as of that stream token, we raise a 403 SynapseError. If None, returns the current state based on the current_state_events table. - is_guest: whether this user is a guest Returns: A list of dicts representing state events. [{}, {}, {}] Raises: @@ -191,6 +189,7 @@ class MessageHandler: members of this room. """ state_filter = state_filter or StateFilter.all() + user_id = requester.user.to_string() if at_token: last_event_id = ( @@ -223,7 +222,7 @@ class MessageHandler: membership, membership_event_id, ) = await self.auth.check_user_in_room_or_world_readable( - room_id, user_id, allow_departed_users=True + room_id, requester, allow_departed_users=True ) if membership == Membership.JOIN: @@ -317,12 +316,11 @@ class MessageHandler: Returns: A dict of user_id to profile info """ - user_id = requester.user.to_string() if not requester.app_service: # We check AS auth after fetching the room membership, as it # requires us to pull out all joined members anyway. membership, _ = await self.auth.check_user_in_room_or_world_readable( - room_id, user_id, allow_departed_users=True + room_id, requester, allow_departed_users=True ) if membership != Membership.JOIN: raise SynapseError( @@ -331,12 +329,19 @@ class MessageHandler: msg="Getting joined members while not being a current member of the room is forbidden.", ) - users_with_profile = await self.store.get_users_in_room_with_profiles(room_id) + users_with_profile = ( + await self._state_storage_controller.get_users_in_room_with_profiles( + room_id + ) + ) # If this is an AS, double check that they are allowed to see the members. # This can either be because the AS user is in the room or because there # is a user in the room that the AS is "interested in" - if requester.app_service and user_id not in users_with_profile: + if ( + requester.app_service + and requester.user.to_string() not in users_with_profile + ): for uid in users_with_profile: if requester.app_service.is_interested_in_user(uid): break @@ -847,8 +852,10 @@ class EventCreationHandler: async def _is_server_notices_room(self, room_id: str) -> bool: if self.config.servernotices.server_notices_mxid is None: return False - user_ids = await self.store.get_users_in_room(room_id) - return self.config.servernotices.server_notices_mxid in user_ids + is_server_notices_room = await self.store.check_local_user_in_room( + user_id=self.config.servernotices.server_notices_mxid, room_id=room_id + ) + return is_server_notices_room async def assert_accepted_privacy_policy(self, requester: Requester) -> None: """Check if a user has accepted the privacy policy diff --git a/synapse/handlers/pagination.py b/synapse/handlers/pagination.py index e1e34e3b16..74e944bce7 100644 --- a/synapse/handlers/pagination.py +++ b/synapse/handlers/pagination.py @@ -464,7 +464,7 @@ class PaginationHandler: membership, member_event_id, ) = await self.auth.check_user_in_room_or_world_readable( - room_id, user_id, allow_departed_users=True + room_id, requester, allow_departed_users=True ) if pagin_config.direction == "b": diff --git a/synapse/handlers/presence.py b/synapse/handlers/presence.py index 741504ba9f..4e575ffbaa 100644 --- a/synapse/handlers/presence.py +++ b/synapse/handlers/presence.py @@ -2051,8 +2051,7 @@ async def get_interested_remotes( ) for room_id, states in room_ids_to_states.items(): - user_ids = await store.get_users_in_room(room_id) - hosts = {get_domain_from_id(user_id) for user_id in user_ids} + hosts = await store.get_current_hosts_in_room(room_id) for host in hosts: hosts_and_states.setdefault(host, set()).update(states) diff --git a/synapse/handlers/register.py b/synapse/handlers/register.py index c77d181722..20ec22105a 100644 --- a/synapse/handlers/register.py +++ b/synapse/handlers/register.py @@ -29,7 +29,13 @@ from synapse.api.constants import ( JoinRules, LoginType, ) -from synapse.api.errors import AuthError, Codes, ConsentNotGivenError, SynapseError +from synapse.api.errors import ( + AuthError, + Codes, + ConsentNotGivenError, + InvalidClientTokenError, + SynapseError, +) from synapse.appservice import ApplicationService from synapse.config.server import is_threepid_reserved from synapse.http.servlet import assert_params_in_dict @@ -180,10 +186,7 @@ class RegistrationHandler: ) if guest_access_token: user_data = await self.auth.get_user_by_access_token(guest_access_token) - if ( - not user_data.is_guest - or UserID.from_string(user_data.user_id).localpart != localpart - ): + if not user_data.is_guest or user_data.user.localpart != localpart: raise AuthError( 403, "Cannot register taken user ID without valid guest " @@ -618,7 +621,7 @@ class RegistrationHandler: user_id = user.to_string() service = self.store.get_app_service_by_token(as_token) if not service: - raise AuthError(403, "Invalid application service token.") + raise InvalidClientTokenError() if not service.is_interested_in_user(user_id): raise SynapseError( 400, diff --git a/synapse/handlers/relations.py b/synapse/handlers/relations.py index 72d25df8c8..28d7093f08 100644 --- a/synapse/handlers/relations.py +++ b/synapse/handlers/relations.py @@ -103,7 +103,7 @@ class RelationsHandler: # TODO Properly handle a user leaving a room. (_, member_event_id) = await self._auth.check_user_in_room_or_world_readable( - room_id, user_id, allow_departed_users=True + room_id, requester, allow_departed_users=True ) # This gets the original event and checks that a) the event exists and diff --git a/synapse/handlers/room.py b/synapse/handlers/room.py index c5f7e1b286..0970e88ad5 100644 --- a/synapse/handlers/room.py +++ b/synapse/handlers/room.py @@ -722,7 +722,7 @@ class RoomCreationHandler: # allow the server notices mxid to create rooms is_requester_admin = True else: - is_requester_admin = await self.auth.is_server_admin(requester.user) + is_requester_admin = await self.auth.is_server_admin(requester) # Let the third party rules modify the room creation config if needed, or abort # the room creation entirely with an exception. @@ -1358,13 +1358,16 @@ class RoomContextHandler: """ user = requester.user if use_admin_priviledge: - await assert_user_is_admin(self.auth, requester.user) + await assert_user_is_admin(self.auth, requester) before_limit = math.floor(limit / 2.0) after_limit = limit - before_limit - users = await self.store.get_users_in_room(room_id) - is_peeking = user.to_string() not in users + is_user_in_room = await self.store.check_local_user_in_room( + user_id=user.to_string(), room_id=room_id + ) + # The user is peeking if they aren't in the room already + is_peeking = not is_user_in_room async def filter_evts(events: List[EventBase]) -> List[EventBase]: if use_admin_priviledge: diff --git a/synapse/handlers/room_member.py b/synapse/handlers/room_member.py index 70dc69c809..709682622f 100644 --- a/synapse/handlers/room_member.py +++ b/synapse/handlers/room_member.py @@ -179,7 +179,7 @@ class RoomMemberHandler(metaclass=abc.ABCMeta): """Try and join a room that this server is not in Args: - requester + requester: The user making the request, according to the access token. remote_room_hosts: List of servers that can be used to join via. room_id: Room that we are trying to join user: User who is trying to join @@ -689,7 +689,7 @@ class RoomMemberHandler(metaclass=abc.ABCMeta): errcode=Codes.BAD_JSON, ) - if "avatar_url" in content: + if "avatar_url" in content and content.get("avatar_url") is not None: if not await self.profile_handler.check_avatar_size_and_mime_type( content["avatar_url"], ): @@ -744,7 +744,7 @@ class RoomMemberHandler(metaclass=abc.ABCMeta): is_requester_admin = True else: - is_requester_admin = await self.auth.is_server_admin(requester.user) + is_requester_admin = await self.auth.is_server_admin(requester) if not is_requester_admin: if self.config.server.block_non_admin_invites: @@ -868,7 +868,7 @@ class RoomMemberHandler(metaclass=abc.ABCMeta): bypass_spam_checker = True else: - bypass_spam_checker = await self.auth.is_server_admin(requester.user) + bypass_spam_checker = await self.auth.is_server_admin(requester) inviter = await self._get_inviter(target.to_string(), room_id) if ( @@ -1410,7 +1410,7 @@ class RoomMemberHandler(metaclass=abc.ABCMeta): ShadowBanError if the requester has been shadow-banned. """ if self.config.server.block_non_admin_invites: - is_requester_admin = await self.auth.is_server_admin(requester.user) + is_requester_admin = await self.auth.is_server_admin(requester) if not is_requester_admin: raise SynapseError( 403, "Invites have been disabled on this server", Codes.FORBIDDEN @@ -1620,8 +1620,10 @@ class RoomMemberHandler(metaclass=abc.ABCMeta): async def _is_server_notice_room(self, room_id: str) -> bool: if self._server_notices_mxid is None: return False - user_ids = await self.store.get_users_in_room(room_id) - return self._server_notices_mxid in user_ids + is_server_notices_room = await self.store.check_local_user_in_room( + user_id=self._server_notices_mxid, room_id=room_id + ) + return is_server_notices_room class RoomMemberMasterHandler(RoomMemberHandler): @@ -1693,7 +1695,7 @@ class RoomMemberMasterHandler(RoomMemberHandler): check_complexity and self.hs.config.server.limit_remote_rooms.admins_can_join ): - check_complexity = not await self.auth.is_server_admin(user) + check_complexity = not await self.store.is_server_admin(user) if check_complexity: # Fetch the room complexity diff --git a/synapse/handlers/sync.py b/synapse/handlers/sync.py index 3ca01391c9..2d95b1fa24 100644 --- a/synapse/handlers/sync.py +++ b/synapse/handlers/sync.py @@ -16,9 +16,11 @@ import logging from typing import ( TYPE_CHECKING, Any, + Collection, Dict, FrozenSet, List, + Mapping, Optional, Sequence, Set, @@ -517,10 +519,17 @@ class SyncHandler: # ensure that we always include current state in the timeline current_state_ids: FrozenSet[str] = frozenset() if any(e.is_state() for e in recents): + # FIXME(faster_joins): We use the partial state here as + # we don't want to block `/sync` on finishing a lazy join. + # Which should be fine once + # https://github.com/matrix-org/synapse/issues/12989 is resolved, + # since we shouldn't reach here anymore? + # Note that we use the current state as a whitelist for filtering + # `recents`, so partial state is only a problem when a membership + # event turns up in `recents` but has not made it into the current + # state. current_state_ids_map = ( - await self._state_storage_controller.get_current_state_ids( - room_id - ) + await self.store.get_partial_current_state_ids(room_id) ) current_state_ids = frozenset(current_state_ids_map.values()) @@ -589,7 +598,13 @@ class SyncHandler: if any(e.is_state() for e in loaded_recents): # FIXME(faster_joins): We use the partial state here as # we don't want to block `/sync` on finishing a lazy join. - # Is this the correct way of doing it? + # Which should be fine once + # https://github.com/matrix-org/synapse/issues/12989 is resolved, + # since we shouldn't reach here anymore? + # Note that we use the current state as a whitelist for filtering + # `loaded_recents`, so partial state is only a problem when a + # membership event turns up in `loaded_recents` but has not made it + # into the current state. current_state_ids_map = ( await self.store.get_partial_current_state_ids(room_id) ) @@ -637,7 +652,10 @@ class SyncHandler: ) async def get_state_after_event( - self, event_id: str, state_filter: Optional[StateFilter] = None + self, + event_id: str, + state_filter: Optional[StateFilter] = None, + await_full_state: bool = True, ) -> StateMap[str]: """ Get the room state after the given event @@ -645,9 +663,14 @@ class SyncHandler: Args: event_id: event of interest state_filter: The state filter used to fetch state from the database. + await_full_state: if `True`, will block if we do not yet have complete state + at the event and `state_filter` is not satisfied by partial state. + Defaults to `True`. """ state_ids = await self._state_storage_controller.get_state_ids_for_event( - event_id, state_filter=state_filter or StateFilter.all() + event_id, + state_filter=state_filter or StateFilter.all(), + await_full_state=await_full_state, ) # using get_metadata_for_events here (instead of get_event) sidesteps an issue @@ -670,6 +693,7 @@ class SyncHandler: room_id: str, stream_position: StreamToken, state_filter: Optional[StateFilter] = None, + await_full_state: bool = True, ) -> StateMap[str]: """Get the room state at a particular stream position @@ -677,6 +701,9 @@ class SyncHandler: room_id: room for which to get state stream_position: point at which to get state state_filter: The state filter used to fetch state from the database. + await_full_state: if `True`, will block if we do not yet have complete state + at the last event in the room before `stream_position` and + `state_filter` is not satisfied by partial state. Defaults to `True`. """ # FIXME: This gets the state at the latest event before the stream ordering, # which might not be the same as the "current state" of the room at the time @@ -688,7 +715,9 @@ class SyncHandler: if last_event_id: state = await self.get_state_after_event( - last_event_id, state_filter=state_filter or StateFilter.all() + last_event_id, + state_filter=state_filter or StateFilter.all(), + await_full_state=await_full_state, ) else: @@ -891,7 +920,15 @@ class SyncHandler: with Measure(self.clock, "compute_state_delta"): # The memberships needed for events in the timeline. # Only calculated when `lazy_load_members` is on. - members_to_fetch = None + members_to_fetch: Optional[Set[str]] = None + + # A dictionary mapping user IDs to the first event in the timeline sent by + # them. Only calculated when `lazy_load_members` is on. + first_event_by_sender_map: Optional[Dict[str, EventBase]] = None + + # The contribution to the room state from state events in the timeline. + # Only contains the last event for any given state key. + timeline_state: StateMap[str] lazy_load_members = sync_config.filter_collection.lazy_load_members() include_redundant_members = ( @@ -902,10 +939,23 @@ class SyncHandler: # We only request state for the members needed to display the # timeline: - members_to_fetch = { - event.sender # FIXME: we also care about invite targets etc. - for event in batch.events - } + timeline_state = {} + + members_to_fetch = set() + first_event_by_sender_map = {} + for event in batch.events: + # Build the map from user IDs to the first timeline event they sent. + if event.sender not in first_event_by_sender_map: + first_event_by_sender_map[event.sender] = event + + # We need the event's sender, unless their membership was in a + # previous timeline event. + if (EventTypes.Member, event.sender) not in timeline_state: + members_to_fetch.add(event.sender) + # FIXME: we also care about invite targets etc. + + if event.is_state(): + timeline_state[(event.type, event.state_key)] = event.event_id if full_state: # always make sure we LL ourselves so we know we're in the room @@ -915,16 +965,21 @@ class SyncHandler: members_to_fetch.add(sync_config.user.to_string()) state_filter = StateFilter.from_lazy_load_member_list(members_to_fetch) + + # We are happy to use partial state to compute the `/sync` response. + # Since partial state may not include the lazy-loaded memberships we + # require, we fix up the state response afterwards with memberships from + # auth events. + await_full_state = False else: - state_filter = StateFilter.all() + timeline_state = { + (event.type, event.state_key): event.event_id + for event in batch.events + if event.is_state() + } - # The contribution to the room state from state events in the timeline. - # Only contains the last event for any given state key. - timeline_state = { - (event.type, event.state_key): event.event_id - for event in batch.events - if event.is_state() - } + state_filter = StateFilter.all() + await_full_state = True # Now calculate the state to return in the sync response for the room. # This is more or less the change in state between the end of the previous @@ -936,19 +991,26 @@ class SyncHandler: if batch: state_at_timeline_end = ( await self._state_storage_controller.get_state_ids_for_event( - batch.events[-1].event_id, state_filter=state_filter + batch.events[-1].event_id, + state_filter=state_filter, + await_full_state=await_full_state, ) ) state_at_timeline_start = ( await self._state_storage_controller.get_state_ids_for_event( - batch.events[0].event_id, state_filter=state_filter + batch.events[0].event_id, + state_filter=state_filter, + await_full_state=await_full_state, ) ) else: state_at_timeline_end = await self.get_state_at( - room_id, stream_position=now_token, state_filter=state_filter + room_id, + stream_position=now_token, + state_filter=state_filter, + await_full_state=await_full_state, ) state_at_timeline_start = state_at_timeline_end @@ -964,14 +1026,19 @@ class SyncHandler: if batch: state_at_timeline_start = ( await self._state_storage_controller.get_state_ids_for_event( - batch.events[0].event_id, state_filter=state_filter + batch.events[0].event_id, + state_filter=state_filter, + await_full_state=await_full_state, ) ) else: # We can get here if the user has ignored the senders of all # the recent events. state_at_timeline_start = await self.get_state_at( - room_id, stream_position=now_token, state_filter=state_filter + room_id, + stream_position=now_token, + state_filter=state_filter, + await_full_state=await_full_state, ) # for now, we disable LL for gappy syncs - see @@ -993,20 +1060,28 @@ class SyncHandler: # is indeed the case. assert since_token is not None state_at_previous_sync = await self.get_state_at( - room_id, stream_position=since_token, state_filter=state_filter + room_id, + stream_position=since_token, + state_filter=state_filter, + await_full_state=await_full_state, ) if batch: state_at_timeline_end = ( await self._state_storage_controller.get_state_ids_for_event( - batch.events[-1].event_id, state_filter=state_filter + batch.events[-1].event_id, + state_filter=state_filter, + await_full_state=await_full_state, ) ) else: # We can get here if the user has ignored the senders of all # the recent events. state_at_timeline_end = await self.get_state_at( - room_id, stream_position=now_token, state_filter=state_filter + room_id, + stream_position=now_token, + state_filter=state_filter, + await_full_state=await_full_state, ) state_ids = _calculate_state( @@ -1036,8 +1111,23 @@ class SyncHandler: (EventTypes.Member, member) for member in members_to_fetch ), + await_full_state=False, ) + # If we only have partial state for the room, `state_ids` may be missing the + # memberships we wanted. We attempt to find some by digging through the auth + # events of timeline events. + if lazy_load_members and await self.store.is_partial_state_room(room_id): + assert members_to_fetch is not None + assert first_event_by_sender_map is not None + + additional_state_ids = ( + await self._find_missing_partial_state_memberships( + room_id, members_to_fetch, first_event_by_sender_map, state_ids + ) + ) + state_ids = {**state_ids, **additional_state_ids} + # At this point, if `lazy_load_members` is enabled, `state_ids` includes # the memberships of all event senders in the timeline. This is because we # may not have sent the memberships in a previous sync. @@ -1086,6 +1176,99 @@ class SyncHandler: if e.type != EventTypes.Aliases # until MSC2261 or alternative solution } + async def _find_missing_partial_state_memberships( + self, + room_id: str, + members_to_fetch: Collection[str], + events_with_membership_auth: Mapping[str, EventBase], + found_state_ids: StateMap[str], + ) -> StateMap[str]: + """Finds missing memberships from a set of auth events and returns them as a + state map. + + Args: + room_id: The partial state room to find the remaining memberships for. + members_to_fetch: The memberships to find. + events_with_membership_auth: A mapping from user IDs to events whose auth + events are known to contain their membership. + found_state_ids: A dict from (type, state_key) -> state_event_id, containing + memberships that have been previously found. Entries in + `members_to_fetch` that have a membership in `found_state_ids` are + ignored. + + Returns: + A dict from ("m.room.member", state_key) -> state_event_id, containing the + memberships missing from `found_state_ids`. + + Raises: + KeyError: if `events_with_membership_auth` does not have an entry for a + missing membership. Memberships in `found_state_ids` do not need an + entry in `events_with_membership_auth`. + """ + additional_state_ids: MutableStateMap[str] = {} + + # Tracks the missing members for logging purposes. + missing_members = set() + + # Identify memberships missing from `found_state_ids` and pick out the auth + # events in which to look for them. + auth_event_ids: Set[str] = set() + for member in members_to_fetch: + if (EventTypes.Member, member) in found_state_ids: + continue + + missing_members.add(member) + event_with_membership_auth = events_with_membership_auth[member] + auth_event_ids.update(event_with_membership_auth.auth_event_ids()) + + auth_events = await self.store.get_events(auth_event_ids) + + # Run through the missing memberships once more, picking out the memberships + # from the pile of auth events we have just fetched. + for member in members_to_fetch: + if (EventTypes.Member, member) in found_state_ids: + continue + + event_with_membership_auth = events_with_membership_auth[member] + + # Dig through the auth events to find the desired membership. + for auth_event_id in event_with_membership_auth.auth_event_ids(): + # We only store events once we have all their auth events, + # so the auth event must be in the pile we have just + # fetched. + auth_event = auth_events[auth_event_id] + + if ( + auth_event.type == EventTypes.Member + and auth_event.state_key == member + ): + missing_members.remove(member) + additional_state_ids[ + (EventTypes.Member, member) + ] = auth_event.event_id + break + + if missing_members: + # There really shouldn't be any missing memberships now. Either: + # * we couldn't find an auth event, which shouldn't happen because we do + # not persist events with persisting their auth events first, or + # * the set of auth events did not contain a membership we wanted, which + # means our caller didn't compute the events in `members_to_fetch` + # correctly, or we somehow accepted an event whose auth events were + # dodgy. + logger.error( + "Failed to find memberships for %s in partial state room " + "%s in the auth events of %s.", + missing_members, + room_id, + [ + events_with_membership_auth[member].event_id + for member in missing_members + ], + ) + + return additional_state_ids + async def unread_notifs_for_room_id( self, room_id: str, sync_config: SyncConfig ) -> NotifCounts: @@ -1730,7 +1913,11 @@ class SyncHandler: continue if room_id in sync_result_builder.joined_room_ids or has_join: - old_state_ids = await self.get_state_at(room_id, since_token) + old_state_ids = await self.get_state_at( + room_id, + since_token, + state_filter=StateFilter.from_types([(EventTypes.Member, user_id)]), + ) old_mem_ev_id = old_state_ids.get((EventTypes.Member, user_id), None) old_mem_ev = None if old_mem_ev_id: @@ -1756,7 +1943,13 @@ class SyncHandler: newly_left_rooms.append(room_id) else: if not old_state_ids: - old_state_ids = await self.get_state_at(room_id, since_token) + old_state_ids = await self.get_state_at( + room_id, + since_token, + state_filter=StateFilter.from_types( + [(EventTypes.Member, user_id)] + ), + ) old_mem_ev_id = old_state_ids.get( (EventTypes.Member, user_id), None ) @@ -2228,10 +2421,10 @@ class SyncHandler: joined_room.room_id, joined_room.event_pos.stream ) ) - users_in_room = await self.state.get_current_users_in_room( + user_ids_in_room = await self.state.get_current_user_ids_in_room( joined_room.room_id, extrems ) - if user_id in users_in_room: + if user_id in user_ids_in_room: joined_room_ids.add(joined_room.room_id) return frozenset(joined_room_ids) diff --git a/synapse/handlers/typing.py b/synapse/handlers/typing.py index 27aa0d3126..a4cd8b8f0c 100644 --- a/synapse/handlers/typing.py +++ b/synapse/handlers/typing.py @@ -26,7 +26,7 @@ from synapse.metrics.background_process_metrics import ( ) from synapse.replication.tcp.streams import TypingStream from synapse.streams import EventSource -from synapse.types import JsonDict, Requester, StreamKeyType, UserID, get_domain_from_id +from synapse.types import JsonDict, Requester, StreamKeyType, UserID from synapse.util.caches.stream_change_cache import StreamChangeCache from synapse.util.metrics import Measure from synapse.util.wheel_timer import WheelTimer @@ -253,12 +253,11 @@ class TypingWriterHandler(FollowerTypingHandler): self, target_user: UserID, requester: Requester, room_id: str, timeout: int ) -> None: target_user_id = target_user.to_string() - auth_user_id = requester.user.to_string() if not self.is_mine_id(target_user_id): raise SynapseError(400, "User is not hosted on this homeserver") - if target_user_id != auth_user_id: + if target_user != requester.user: raise AuthError(400, "Cannot set another user's typing state") if requester.shadow_banned: @@ -266,7 +265,7 @@ class TypingWriterHandler(FollowerTypingHandler): await self.clock.sleep(random.randint(1, 10)) raise ShadowBanError() - await self.auth.check_user_in_room(room_id, target_user_id) + await self.auth.check_user_in_room(room_id, requester) logger.debug("%s has started typing in %s", target_user_id, room_id) @@ -289,12 +288,11 @@ class TypingWriterHandler(FollowerTypingHandler): self, target_user: UserID, requester: Requester, room_id: str ) -> None: target_user_id = target_user.to_string() - auth_user_id = requester.user.to_string() if not self.is_mine_id(target_user_id): raise SynapseError(400, "User is not hosted on this homeserver") - if target_user_id != auth_user_id: + if target_user != requester.user: raise AuthError(400, "Cannot set another user's typing state") if requester.shadow_banned: @@ -302,7 +300,7 @@ class TypingWriterHandler(FollowerTypingHandler): await self.clock.sleep(random.randint(1, 10)) raise ShadowBanError() - await self.auth.check_user_in_room(room_id, target_user_id) + await self.auth.check_user_in_room(room_id, requester) logger.debug("%s has stopped typing in %s", target_user_id, room_id) @@ -364,8 +362,9 @@ class TypingWriterHandler(FollowerTypingHandler): ) return - users = await self.store.get_users_in_room(room_id) - domains = {get_domain_from_id(u) for u in users} + domains = await self._storage_controllers.state.get_current_hosts_in_room( + room_id + ) if self.server_name in domains: logger.info("Got typing update from %s: %r", user_id, content) diff --git a/synapse/handlers/ui_auth/checkers.py b/synapse/handlers/ui_auth/checkers.py index 05cebb5d4d..a744d68c64 100644 --- a/synapse/handlers/ui_auth/checkers.py +++ b/synapse/handlers/ui_auth/checkers.py @@ -19,7 +19,6 @@ from twisted.web.client import PartialDownloadError from synapse.api.constants import LoginType from synapse.api.errors import Codes, LoginError, SynapseError -from synapse.config.emailconfig import ThreepidBehaviour from synapse.util import json_decoder if TYPE_CHECKING: @@ -153,7 +152,7 @@ class _BaseThreepidAuthChecker: logger.info("Getting validated threepid. threepidcreds: %r", (threepid_creds,)) - # msisdns are currently always ThreepidBehaviour.REMOTE + # msisdns are currently always verified via the IS if medium == "msisdn": if not self.hs.config.registration.account_threepid_delegate_msisdn: raise SynapseError( @@ -164,18 +163,7 @@ class _BaseThreepidAuthChecker: threepid_creds, ) elif medium == "email": - if ( - self.hs.config.email.threepid_behaviour_email - == ThreepidBehaviour.REMOTE - ): - assert self.hs.config.registration.account_threepid_delegate_email - threepid = await identity_handler.threepid_from_creds( - self.hs.config.registration.account_threepid_delegate_email, - threepid_creds, - ) - elif ( - self.hs.config.email.threepid_behaviour_email == ThreepidBehaviour.LOCAL - ): + if self.hs.config.email.can_verify_email: threepid = None row = await self.store.get_threepid_validation_session( medium, @@ -227,10 +215,7 @@ class EmailIdentityAuthChecker(UserInteractiveAuthChecker, _BaseThreepidAuthChec _BaseThreepidAuthChecker.__init__(self, hs) def is_enabled(self) -> bool: - return self.hs.config.email.threepid_behaviour_email in ( - ThreepidBehaviour.REMOTE, - ThreepidBehaviour.LOCAL, - ) + return self.hs.config.email.can_verify_email async def check_auth(self, authdict: dict, clientip: str) -> Any: return await self._check_threepid("email", authdict) diff --git a/synapse/http/servlet.py b/synapse/http/servlet.py index 4ff840ca0e..26aaabfb34 100644 --- a/synapse/http/servlet.py +++ b/synapse/http/servlet.py @@ -23,9 +23,12 @@ from typing import ( Optional, Sequence, Tuple, + Type, + TypeVar, overload, ) +from pydantic import BaseModel, ValidationError from typing_extensions import Literal from twisted.web.server import Request @@ -694,6 +697,28 @@ def parse_json_object_from_request( return content +Model = TypeVar("Model", bound=BaseModel) + + +def parse_and_validate_json_object_from_request( + request: Request, model_type: Type[Model] +) -> Model: + """Parse a JSON object from the body of a twisted HTTP request, then deserialise and + validate using the given pydantic model. + + Raises: + SynapseError if the request body couldn't be decoded as JSON or + if it wasn't a JSON object. + """ + content = parse_json_object_from_request(request, allow_empty_body=False) + try: + instance = model_type.parse_obj(content) + except ValidationError as e: + raise SynapseError(HTTPStatus.BAD_REQUEST, str(e), errcode=Codes.BAD_JSON) + + return instance + + def assert_params_in_dict(body: JsonDict, required: Iterable[str]) -> None: absent = [] for k in required: diff --git a/synapse/http/site.py b/synapse/http/site.py index eeec74b78a..1155f3f610 100644 --- a/synapse/http/site.py +++ b/synapse/http/site.py @@ -226,7 +226,7 @@ class SynapseRequest(Request): # If this is a request where the target user doesn't match the user who # authenticated (e.g. and admin is puppetting a user) then we return both. - if self._requester.user.to_string() != authenticated_entity: + if requester != authenticated_entity: return requester, authenticated_entity return requester, None diff --git a/synapse/logging/opentracing.py b/synapse/logging/opentracing.py index d1fa2cf8ae..482316a1ff 100644 --- a/synapse/logging/opentracing.py +++ b/synapse/logging/opentracing.py @@ -310,6 +310,19 @@ class SynapseTags: # The name of the external cache CACHE_NAME = "cache.name" + # Used to tag function arguments + # + # Tag a named arg. The name of the argument should be appended to this prefix. + FUNC_ARG_PREFIX = "ARG." + # Tag extra variadic number of positional arguments (`def foo(first, second, *extras)`) + FUNC_ARGS = "args" + # Tag keyword args + FUNC_KWARGS = "kwargs" + + # Some intermediate result that's interesting to the function. The label for + # the result should be appended to this prefix. + RESULT_PREFIX = "RESULT." + class SynapseBaggage: FORCE_TRACING = "synapse-force-tracing" @@ -967,9 +980,9 @@ def tag_args(func: Callable[P, R]) -> Callable[P, R]: # first argument only if it's named `self` or `cls`. This isn't fool-proof # but handles the idiomatic cases. for i, arg in enumerate(args[1:], start=1): # type: ignore[index] - set_tag("ARG_" + argspec.args[i], str(arg)) - set_tag("args", str(args[len(argspec.args) :])) # type: ignore[index] - set_tag("kwargs", str(kwargs)) + set_tag(SynapseTags.FUNC_ARG_PREFIX + argspec.args[i], str(arg)) + set_tag(SynapseTags.FUNC_ARGS, str(args[len(argspec.args) :])) # type: ignore[index] + set_tag(SynapseTags.FUNC_KWARGS, str(kwargs)) yield return _custom_sync_async_decorator(func, _wrapping_logic) diff --git a/synapse/metrics/__init__.py b/synapse/metrics/__init__.py index 496fce2ecc..c3d3daf877 100644 --- a/synapse/metrics/__init__.py +++ b/synapse/metrics/__init__.py @@ -46,12 +46,12 @@ from twisted.python.threadpool import ThreadPool # This module is imported for its side effects; flake8 needn't warn that it's unused. import synapse.metrics._reactor_metrics # noqa: F401 -from synapse.metrics._exposition import ( +from synapse.metrics._gc import MIN_TIME_BETWEEN_GCS, install_gc_manager +from synapse.metrics._legacy_exposition import ( MetricsResource, generate_latest, start_http_server, ) -from synapse.metrics._gc import MIN_TIME_BETWEEN_GCS, install_gc_manager from synapse.metrics._types import Collector from synapse.util import SYNAPSE_VERSION diff --git a/synapse/metrics/_exposition.py b/synapse/metrics/_legacy_exposition.py index 353d0a63b6..ff640a49af 100644 --- a/synapse/metrics/_exposition.py +++ b/synapse/metrics/_legacy_exposition.py @@ -80,7 +80,27 @@ def sample_line(line: Sample, name: str) -> str: return "{}{} {}{}\n".format(name, labelstr, floatToGoString(line.value), timestamp) +# Mapping from new metric names to legacy metric names. +# We translate these back to their old names when exposing them through our +# legacy vendored exporter. +# Only this legacy exposition module applies these name changes. +LEGACY_METRIC_NAMES = { + "synapse_util_caches_cache_hits": "synapse_util_caches_cache:hits", + "synapse_util_caches_cache_size": "synapse_util_caches_cache:size", + "synapse_util_caches_cache_evicted_size": "synapse_util_caches_cache:evicted_size", + "synapse_util_caches_cache_total": "synapse_util_caches_cache:total", + "synapse_util_caches_response_cache_size": "synapse_util_caches_response_cache:size", + "synapse_util_caches_response_cache_hits": "synapse_util_caches_response_cache:hits", + "synapse_util_caches_response_cache_evicted_size": "synapse_util_caches_response_cache:evicted_size", + "synapse_util_caches_response_cache_total": "synapse_util_caches_response_cache:total", +} + + def generate_latest(registry: CollectorRegistry, emit_help: bool = False) -> bytes: + """ + Generate metrics in legacy format. Modern metrics are generated directly + by prometheus-client. + """ # Trigger the cache metrics to be rescraped, which updates the common # metrics but do not produce metrics themselves @@ -94,7 +114,8 @@ def generate_latest(registry: CollectorRegistry, emit_help: bool = False) -> byt # No samples, don't bother. continue - mname = metric.name + # Translate to legacy metric name if it has one. + mname = LEGACY_METRIC_NAMES.get(metric.name, metric.name) mnewname = metric.name mtype = metric.type @@ -124,7 +145,7 @@ def generate_latest(registry: CollectorRegistry, emit_help: bool = False) -> byt om_samples: Dict[str, List[str]] = {} for s in metric.samples: for suffix in ["_created", "_gsum", "_gcount"]: - if s.name == metric.name + suffix: + if s.name == mname + suffix: # OpenMetrics specific sample, put in a gauge at the end. # (these come from gaugehistograms which don't get renamed, # so no need to faff with mnewname) @@ -140,12 +161,12 @@ def generate_latest(registry: CollectorRegistry, emit_help: bool = False) -> byt if emit_help: output.append( "# HELP {}{} {}\n".format( - metric.name, + mname, suffix, metric.documentation.replace("\\", r"\\").replace("\n", r"\n"), ) ) - output.append(f"# TYPE {metric.name}{suffix} gauge\n") + output.append(f"# TYPE {mname}{suffix} gauge\n") output.extend(lines) # Get rid of the weird colon things while we're at it @@ -170,11 +191,12 @@ def generate_latest(registry: CollectorRegistry, emit_help: bool = False) -> byt # Get rid of the OpenMetrics specific samples (we should already have # dealt with them above anyway.) for suffix in ["_created", "_gsum", "_gcount"]: - if s.name == metric.name + suffix: + if s.name == mname + suffix: break else: + sample_name = LEGACY_METRIC_NAMES.get(s.name, s.name) output.append( - sample_line(s, s.name.replace(":total", "").replace(":", "_")) + sample_line(s, sample_name.replace(":total", "").replace(":", "_")) ) return "".join(output).encode("utf-8") diff --git a/synapse/push/baserules.py b/synapse/push/baserules.py index 6c0cc5a6ce..440205e80c 100644 --- a/synapse/push/baserules.py +++ b/synapse/push/baserules.py @@ -14,128 +14,235 @@ # See the License for the specific language governing permissions and # limitations under the License. -import copy -from typing import Any, Dict, List - -from synapse.push.rulekinds import PRIORITY_CLASS_INVERSE_MAP, PRIORITY_CLASS_MAP +""" +Push rules is the system used to determine which events trigger a push (and a +bump in notification counts). + +This consists of a list of "push rules" for each user, where a push rule is a +pair of "conditions" and "actions". When a user receives an event Synapse +iterates over the list of push rules until it finds one where all the conditions +match the event, at which point "actions" describe the outcome (e.g. notify, +highlight, etc). + +Push rules are split up into 5 different "kinds" (aka "priority classes"), which +are run in order: + 1. Override — highest priority rules, e.g. always ignore notices + 2. Content — content specific rules, e.g. @ notifications + 3. Room — per room rules, e.g. enable/disable notifications for all messages + in a room + 4. Sender — per sender rules, e.g. never notify for messages from a given + user + 5. Underride — the lowest priority "default" rules, e.g. notify for every + message. + +The set of "base rules" are the list of rules that every user has by default. A +user can modify their copy of the push rules in one of three ways: + + 1. Adding a new push rule of a certain kind + 2. Changing the actions of a base rule + 3. Enabling/disabling a base rule. + +The base rules are split into whether they come before or after a particular +kind, so the order of push rule evaluation would be: base rules for before +"override" kind, user defined "override" rules, base rules after "override" +kind, etc, etc. +""" + +import itertools +import logging +from typing import Dict, Iterator, List, Mapping, Sequence, Tuple, Union + +import attr + +from synapse.config.experimental import ExperimentalConfig +from synapse.push.rulekinds import PRIORITY_CLASS_MAP + +logger = logging.getLogger(__name__) + + +@attr.s(auto_attribs=True, slots=True, frozen=True) +class PushRule: + """A push rule + + Attributes: + rule_id: a unique ID for this rule + priority_class: what "kind" of push rule this is (see + `PRIORITY_CLASS_MAP` for mapping between int and kind) + conditions: the sequence of conditions that all need to match + actions: the actions to apply if all conditions are met + default: is this a base rule? + default_enabled: is this enabled by default? + """ + rule_id: str + priority_class: int + conditions: Sequence[Mapping[str, str]] + actions: Sequence[Union[str, Mapping]] + default: bool = False + default_enabled: bool = True -def list_with_base_rules(rawrules: List[Dict[str, Any]]) -> List[Dict[str, Any]]: - """Combine the list of rules set by the user with the default push rules - Args: - rawrules: The rules the user has modified or set. +@attr.s(auto_attribs=True, slots=True, frozen=True, weakref_slot=False) +class PushRules: + """A collection of push rules for an account. - Returns: - A new list with the rules set by the user combined with the defaults. + Can be iterated over, producing push rules in priority order. """ - ruleslist = [] - # Grab the base rules that the user has modified. - # The modified base rules have a priority_class of -1. - modified_base_rules = {r["rule_id"]: r for r in rawrules if r["priority_class"] < 0} + # A mapping from rule ID to push rule that overrides a base rule. These will + # be returned instead of the base rule. + overriden_base_rules: Dict[str, PushRule] = attr.Factory(dict) + + # The following stores the custom push rules at each priority class. + # + # We keep these separate (rather than combining into one big list) to avoid + # copying the base rules around all the time. + override: List[PushRule] = attr.Factory(list) + content: List[PushRule] = attr.Factory(list) + room: List[PushRule] = attr.Factory(list) + sender: List[PushRule] = attr.Factory(list) + underride: List[PushRule] = attr.Factory(list) + + def __iter__(self) -> Iterator[PushRule]: + # When iterating over the push rules we need to return the base rules + # interspersed at the correct spots. + for rule in itertools.chain( + BASE_PREPEND_OVERRIDE_RULES, + self.override, + BASE_APPEND_OVERRIDE_RULES, + self.content, + BASE_APPEND_CONTENT_RULES, + self.room, + self.sender, + self.underride, + BASE_APPEND_UNDERRIDE_RULES, + ): + # Check if a base rule has been overriden by a custom rule. If so + # return that instead. + override_rule = self.overriden_base_rules.get(rule.rule_id) + if override_rule: + yield override_rule + else: + yield rule + + def __len__(self) -> int: + # The length is mostly used by caches to get a sense of "size" / amount + # of memory this object is using, so we only count the number of custom + # rules. + return ( + len(self.overriden_base_rules) + + len(self.override) + + len(self.content) + + len(self.room) + + len(self.sender) + + len(self.underride) + ) - # Remove the modified base rules from the list, They'll be added back - # in the default positions in the list. - rawrules = [r for r in rawrules if r["priority_class"] >= 0] - # shove the server default rules for each kind onto the end of each - current_prio_class = list(PRIORITY_CLASS_INVERSE_MAP)[-1] +@attr.s(auto_attribs=True, slots=True, frozen=True, weakref_slot=False) +class FilteredPushRules: + """A wrapper around `PushRules` that filters out disabled experimental push + rules, and includes the "enabled" state for each rule when iterated over. + """ - ruleslist.extend( - make_base_prepend_rules( - PRIORITY_CLASS_INVERSE_MAP[current_prio_class], modified_base_rules - ) - ) + push_rules: PushRules + enabled_map: Dict[str, bool] + experimental_config: ExperimentalConfig - for r in rawrules: - if r["priority_class"] < current_prio_class: - while r["priority_class"] < current_prio_class: - ruleslist.extend( - make_base_append_rules( - PRIORITY_CLASS_INVERSE_MAP[current_prio_class], - modified_base_rules, - ) - ) - current_prio_class -= 1 - if current_prio_class > 0: - ruleslist.extend( - make_base_prepend_rules( - PRIORITY_CLASS_INVERSE_MAP[current_prio_class], - modified_base_rules, - ) - ) - - ruleslist.append(r) - - while current_prio_class > 0: - ruleslist.extend( - make_base_append_rules( - PRIORITY_CLASS_INVERSE_MAP[current_prio_class], modified_base_rules - ) - ) - current_prio_class -= 1 - if current_prio_class > 0: - ruleslist.extend( - make_base_prepend_rules( - PRIORITY_CLASS_INVERSE_MAP[current_prio_class], modified_base_rules - ) - ) + def __iter__(self) -> Iterator[Tuple[PushRule, bool]]: + for rule in self.push_rules: + if not _is_experimental_rule_enabled( + rule.rule_id, self.experimental_config + ): + continue - return ruleslist + enabled = self.enabled_map.get(rule.rule_id, rule.default_enabled) + yield rule, enabled -def make_base_append_rules( - kind: str, modified_base_rules: Dict[str, Dict[str, Any]] -) -> List[Dict[str, Any]]: - rules = [] + def __len__(self) -> int: + return len(self.push_rules) - if kind == "override": - rules = BASE_APPEND_OVERRIDE_RULES - elif kind == "underride": - rules = BASE_APPEND_UNDERRIDE_RULES - elif kind == "content": - rules = BASE_APPEND_CONTENT_RULES - # Copy the rules before modifying them - rules = copy.deepcopy(rules) - for r in rules: - # Only modify the actions, keep the conditions the same. - assert isinstance(r["rule_id"], str) - modified = modified_base_rules.get(r["rule_id"]) - if modified: - r["actions"] = modified["actions"] +DEFAULT_EMPTY_PUSH_RULES = PushRules() - return rules +def compile_push_rules(rawrules: List[PushRule]) -> PushRules: + """Given a set of custom push rules return a `PushRules` instance (which + includes the base rules). + """ + + if not rawrules: + # Fast path to avoid allocating empty lists when there are no custom + # rules for the user. + return DEFAULT_EMPTY_PUSH_RULES + + rules = PushRules() -def make_base_prepend_rules( - kind: str, - modified_base_rules: Dict[str, Dict[str, Any]], -) -> List[Dict[str, Any]]: - rules = [] + for rule in rawrules: + # We need to decide which bucket each custom push rule goes into. - if kind == "override": - rules = BASE_PREPEND_OVERRIDE_RULES + # If it has the same ID as a base rule then it overrides that... + overriden_base_rule = BASE_RULES_BY_ID.get(rule.rule_id) + if overriden_base_rule: + rules.overriden_base_rules[rule.rule_id] = attr.evolve( + overriden_base_rule, actions=rule.actions + ) + continue + + # ... otherwise it gets added to the appropriate priority class bucket + collection: List[PushRule] + if rule.priority_class == 5: + collection = rules.override + elif rule.priority_class == 4: + collection = rules.content + elif rule.priority_class == 3: + collection = rules.room + elif rule.priority_class == 2: + collection = rules.sender + elif rule.priority_class == 1: + collection = rules.underride + elif rule.priority_class <= 0: + logger.info( + "Got rule with priority class less than zero, but doesn't override a base rule: %s", + rule, + ) + continue + else: + # We log and continue here so as not to break event sending + logger.error("Unknown priority class: %", rule.priority_class) + continue - # Copy the rules before modifying them - rules = copy.deepcopy(rules) - for r in rules: - # Only modify the actions, keep the conditions the same. - assert isinstance(r["rule_id"], str) - modified = modified_base_rules.get(r["rule_id"]) - if modified: - r["actions"] = modified["actions"] + collection.append(rule) return rules -# We have to annotate these types, otherwise mypy infers them as -# `List[Dict[str, Sequence[Collection[str]]]]`. -BASE_APPEND_CONTENT_RULES: List[Dict[str, Any]] = [ - { - "rule_id": "global/content/.m.rule.contains_user_name", - "conditions": [ +def _is_experimental_rule_enabled( + rule_id: str, experimental_config: ExperimentalConfig +) -> bool: + """Used by `FilteredPushRules` to filter out experimental rules when they + have not been enabled. + """ + if ( + rule_id == "global/override/.org.matrix.msc3786.rule.room.server_acl" + and not experimental_config.msc3786_enabled + ): + return False + if ( + rule_id == "global/underride/.org.matrix.msc3772.thread_reply" + and not experimental_config.msc3772_enabled + ): + return False + return True + + +BASE_APPEND_CONTENT_RULES = [ + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["content"], + rule_id="global/content/.m.rule.contains_user_name", + conditions=[ { "kind": "event_match", "key": "content.body", @@ -143,29 +250,33 @@ BASE_APPEND_CONTENT_RULES: List[Dict[str, Any]] = [ "pattern_type": "user_localpart", } ], - "actions": [ + actions=[ "notify", {"set_tweak": "sound", "value": "default"}, {"set_tweak": "highlight"}, ], - } + ) ] -BASE_PREPEND_OVERRIDE_RULES: List[Dict[str, Any]] = [ - { - "rule_id": "global/override/.m.rule.master", - "enabled": False, - "conditions": [], - "actions": ["dont_notify"], - } +BASE_PREPEND_OVERRIDE_RULES = [ + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["override"], + rule_id="global/override/.m.rule.master", + default_enabled=False, + conditions=[], + actions=["dont_notify"], + ) ] -BASE_APPEND_OVERRIDE_RULES: List[Dict[str, Any]] = [ - { - "rule_id": "global/override/.m.rule.suppress_notices", - "conditions": [ +BASE_APPEND_OVERRIDE_RULES = [ + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["override"], + rule_id="global/override/.m.rule.suppress_notices", + conditions=[ { "kind": "event_match", "key": "content.msgtype", @@ -173,13 +284,15 @@ BASE_APPEND_OVERRIDE_RULES: List[Dict[str, Any]] = [ "_cache_key": "_suppress_notices", } ], - "actions": ["dont_notify"], - }, + actions=["dont_notify"], + ), # NB. .m.rule.invite_for_me must be higher prio than .m.rule.member_event # otherwise invites will be matched by .m.rule.member_event - { - "rule_id": "global/override/.m.rule.invite_for_me", - "conditions": [ + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["override"], + rule_id="global/override/.m.rule.invite_for_me", + conditions=[ { "kind": "event_match", "key": "type", @@ -195,21 +308,23 @@ BASE_APPEND_OVERRIDE_RULES: List[Dict[str, Any]] = [ # Match the requester's MXID. {"kind": "event_match", "key": "state_key", "pattern_type": "user_id"}, ], - "actions": [ + actions=[ "notify", {"set_tweak": "sound", "value": "default"}, {"set_tweak": "highlight", "value": False}, ], - }, + ), # Will we sometimes want to know about people joining and leaving? # Perhaps: if so, this could be expanded upon. Seems the most usual case # is that we don't though. We add this override rule so that even if # the room rule is set to notify, we don't get notifications about # join/leave/avatar/displayname events. # See also: https://matrix.org/jira/browse/SYN-607 - { - "rule_id": "global/override/.m.rule.member_event", - "conditions": [ + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["override"], + rule_id="global/override/.m.rule.member_event", + conditions=[ { "kind": "event_match", "key": "type", @@ -217,24 +332,28 @@ BASE_APPEND_OVERRIDE_RULES: List[Dict[str, Any]] = [ "_cache_key": "_member", } ], - "actions": ["dont_notify"], - }, + actions=["dont_notify"], + ), # This was changed from underride to override so it's closer in priority # to the content rules where the user name highlight rule lives. This # way a room rule is lower priority than both but a custom override rule # is higher priority than both. - { - "rule_id": "global/override/.m.rule.contains_display_name", - "conditions": [{"kind": "contains_display_name"}], - "actions": [ + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["override"], + rule_id="global/override/.m.rule.contains_display_name", + conditions=[{"kind": "contains_display_name"}], + actions=[ "notify", {"set_tweak": "sound", "value": "default"}, {"set_tweak": "highlight"}, ], - }, - { - "rule_id": "global/override/.m.rule.roomnotif", - "conditions": [ + ), + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["override"], + rule_id="global/override/.m.rule.roomnotif", + conditions=[ { "kind": "event_match", "key": "content.body", @@ -247,11 +366,13 @@ BASE_APPEND_OVERRIDE_RULES: List[Dict[str, Any]] = [ "_cache_key": "_roomnotif_pl", }, ], - "actions": ["notify", {"set_tweak": "highlight", "value": True}], - }, - { - "rule_id": "global/override/.m.rule.tombstone", - "conditions": [ + actions=["notify", {"set_tweak": "highlight", "value": True}], + ), + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["override"], + rule_id="global/override/.m.rule.tombstone", + conditions=[ { "kind": "event_match", "key": "type", @@ -265,11 +386,13 @@ BASE_APPEND_OVERRIDE_RULES: List[Dict[str, Any]] = [ "_cache_key": "_tombstone_statekey", }, ], - "actions": ["notify", {"set_tweak": "highlight", "value": True}], - }, - { - "rule_id": "global/override/.m.rule.reaction", - "conditions": [ + actions=["notify", {"set_tweak": "highlight", "value": True}], + ), + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["override"], + rule_id="global/override/.m.rule.reaction", + conditions=[ { "kind": "event_match", "key": "type", @@ -277,14 +400,16 @@ BASE_APPEND_OVERRIDE_RULES: List[Dict[str, Any]] = [ "_cache_key": "_reaction", } ], - "actions": ["dont_notify"], - }, + actions=["dont_notify"], + ), # XXX: This is an experimental rule that is only enabled if msc3786_enabled # is enabled, if it is not the rule gets filtered out in _load_rules() in # PushRulesWorkerStore - { - "rule_id": "global/override/.org.matrix.msc3786.rule.room.server_acl", - "conditions": [ + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["override"], + rule_id="global/override/.org.matrix.msc3786.rule.room.server_acl", + conditions=[ { "kind": "event_match", "key": "type", @@ -298,15 +423,17 @@ BASE_APPEND_OVERRIDE_RULES: List[Dict[str, Any]] = [ "_cache_key": "_room_server_acl_state_key", }, ], - "actions": [], - }, + actions=[], + ), ] -BASE_APPEND_UNDERRIDE_RULES: List[Dict[str, Any]] = [ - { - "rule_id": "global/underride/.m.rule.call", - "conditions": [ +BASE_APPEND_UNDERRIDE_RULES = [ + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["underride"], + rule_id="global/underride/.m.rule.call", + conditions=[ { "kind": "event_match", "key": "type", @@ -314,17 +441,19 @@ BASE_APPEND_UNDERRIDE_RULES: List[Dict[str, Any]] = [ "_cache_key": "_call", } ], - "actions": [ + actions=[ "notify", {"set_tweak": "sound", "value": "ring"}, {"set_tweak": "highlight", "value": False}, ], - }, + ), # XXX: once m.direct is standardised everywhere, we should use it to detect # a DM from the user's perspective rather than this heuristic. - { - "rule_id": "global/underride/.m.rule.room_one_to_one", - "conditions": [ + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["underride"], + rule_id="global/underride/.m.rule.room_one_to_one", + conditions=[ {"kind": "room_member_count", "is": "2", "_cache_key": "member_count"}, { "kind": "event_match", @@ -333,17 +462,19 @@ BASE_APPEND_UNDERRIDE_RULES: List[Dict[str, Any]] = [ "_cache_key": "_message", }, ], - "actions": [ + actions=[ "notify", {"set_tweak": "sound", "value": "default"}, {"set_tweak": "highlight", "value": False}, ], - }, + ), # XXX: this is going to fire for events which aren't m.room.messages # but are encrypted (e.g. m.call.*)... - { - "rule_id": "global/underride/.m.rule.encrypted_room_one_to_one", - "conditions": [ + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["underride"], + rule_id="global/underride/.m.rule.encrypted_room_one_to_one", + conditions=[ {"kind": "room_member_count", "is": "2", "_cache_key": "member_count"}, { "kind": "event_match", @@ -352,15 +483,17 @@ BASE_APPEND_UNDERRIDE_RULES: List[Dict[str, Any]] = [ "_cache_key": "_encrypted", }, ], - "actions": [ + actions=[ "notify", {"set_tweak": "sound", "value": "default"}, {"set_tweak": "highlight", "value": False}, ], - }, - { - "rule_id": "global/underride/.org.matrix.msc3772.thread_reply", - "conditions": [ + ), + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["underride"], + rule_id="global/underride/.org.matrix.msc3772.thread_reply", + conditions=[ { "kind": "org.matrix.msc3772.relation_match", "rel_type": "m.thread", @@ -368,11 +501,13 @@ BASE_APPEND_UNDERRIDE_RULES: List[Dict[str, Any]] = [ "sender_type": "user_id", } ], - "actions": ["notify", {"set_tweak": "highlight", "value": False}], - }, - { - "rule_id": "global/underride/.m.rule.message", - "conditions": [ + actions=["notify", {"set_tweak": "highlight", "value": False}], + ), + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["underride"], + rule_id="global/underride/.m.rule.message", + conditions=[ { "kind": "event_match", "key": "type", @@ -380,13 +515,15 @@ BASE_APPEND_UNDERRIDE_RULES: List[Dict[str, Any]] = [ "_cache_key": "_message", } ], - "actions": ["notify", {"set_tweak": "highlight", "value": False}], - }, + actions=["notify", {"set_tweak": "highlight", "value": False}], + ), # XXX: this is going to fire for events which aren't m.room.messages # but are encrypted (e.g. m.call.*)... - { - "rule_id": "global/underride/.m.rule.encrypted", - "conditions": [ + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["underride"], + rule_id="global/underride/.m.rule.encrypted", + conditions=[ { "kind": "event_match", "key": "type", @@ -394,11 +531,13 @@ BASE_APPEND_UNDERRIDE_RULES: List[Dict[str, Any]] = [ "_cache_key": "_encrypted", } ], - "actions": ["notify", {"set_tweak": "highlight", "value": False}], - }, - { - "rule_id": "global/underride/.im.vector.jitsi", - "conditions": [ + actions=["notify", {"set_tweak": "highlight", "value": False}], + ), + PushRule( + default=True, + priority_class=PRIORITY_CLASS_MAP["underride"], + rule_id="global/underride/.im.vector.jitsi", + conditions=[ { "kind": "event_match", "key": "type", @@ -418,29 +557,27 @@ BASE_APPEND_UNDERRIDE_RULES: List[Dict[str, Any]] = [ "_cache_key": "_is_state_event", }, ], - "actions": ["notify", {"set_tweak": "highlight", "value": False}], - }, + actions=["notify", {"set_tweak": "highlight", "value": False}], + ), ] BASE_RULE_IDS = set() +BASE_RULES_BY_ID: Dict[str, PushRule] = {} + for r in BASE_APPEND_CONTENT_RULES: - r["priority_class"] = PRIORITY_CLASS_MAP["content"] - r["default"] = True - BASE_RULE_IDS.add(r["rule_id"]) + BASE_RULE_IDS.add(r.rule_id) + BASE_RULES_BY_ID[r.rule_id] = r for r in BASE_PREPEND_OVERRIDE_RULES: - r["priority_class"] = PRIORITY_CLASS_MAP["override"] - r["default"] = True - BASE_RULE_IDS.add(r["rule_id"]) + BASE_RULE_IDS.add(r.rule_id) + BASE_RULES_BY_ID[r.rule_id] = r for r in BASE_APPEND_OVERRIDE_RULES: - r["priority_class"] = PRIORITY_CLASS_MAP["override"] - r["default"] = True - BASE_RULE_IDS.add(r["rule_id"]) + BASE_RULE_IDS.add(r.rule_id) + BASE_RULES_BY_ID[r.rule_id] = r for r in BASE_APPEND_UNDERRIDE_RULES: - r["priority_class"] = PRIORITY_CLASS_MAP["underride"] - r["default"] = True - BASE_RULE_IDS.add(r["rule_id"]) + BASE_RULE_IDS.add(r.rule_id) + BASE_RULES_BY_ID[r.rule_id] = r diff --git a/synapse/push/bulk_push_rule_evaluator.py b/synapse/push/bulk_push_rule_evaluator.py index 713dcf6950..ccd512be54 100644 --- a/synapse/push/bulk_push_rule_evaluator.py +++ b/synapse/push/bulk_push_rule_evaluator.py @@ -15,7 +15,18 @@ import itertools import logging -from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Set, Tuple, Union +from typing import ( + TYPE_CHECKING, + Collection, + Dict, + Iterable, + List, + Mapping, + Optional, + Set, + Tuple, + Union, +) from prometheus_client import Counter @@ -30,6 +41,7 @@ from synapse.util.caches import register_cache from synapse.util.metrics import measure_func from synapse.visibility import filter_event_for_clients_with_state +from .baserules import FilteredPushRules, PushRule from .push_rule_evaluator import PushRuleEvaluatorForEvent if TYPE_CHECKING: @@ -112,7 +124,7 @@ class BulkPushRuleEvaluator: async def _get_rules_for_event( self, event: EventBase, - ) -> Dict[str, List[Dict[str, Any]]]: + ) -> Dict[str, FilteredPushRules]: """Get the push rules for all users who may need to be notified about the event. @@ -186,7 +198,7 @@ class BulkPushRuleEvaluator: return pl_event.content if pl_event else {}, sender_level async def _get_mutual_relations( - self, event: EventBase, rules: Iterable[Dict[str, Any]] + self, event: EventBase, rules: Iterable[Tuple[PushRule, bool]] ) -> Dict[str, Set[Tuple[str, str]]]: """ Fetch event metadata for events which related to the same event as the given event. @@ -216,12 +228,11 @@ class BulkPushRuleEvaluator: # Pre-filter to figure out which relation types are interesting. rel_types = set() - for rule in rules: - # Skip disabled rules. - if "enabled" in rule and not rule["enabled"]: + for rule, enabled in rules: + if not enabled: continue - for condition in rule["conditions"]: + for condition in rule.conditions: if condition["kind"] != "org.matrix.msc3772.relation_match": continue @@ -254,7 +265,7 @@ class BulkPushRuleEvaluator: count_as_unread = _should_count_as_unread(event, context) rules_by_user = await self._get_rules_for_event(event) - actions_by_user: Dict[str, List[Union[dict, str]]] = {} + actions_by_user: Dict[str, Collection[Union[Mapping, str]]] = {} room_member_count = await self.store.get_number_joined_users_in_room( event.room_id @@ -317,15 +328,13 @@ class BulkPushRuleEvaluator: # current user, it'll be added to the dict later. actions_by_user[uid] = [] - for rule in rules: - if "enabled" in rule and not rule["enabled"]: + for rule, enabled in rules: + if not enabled: continue - matches = evaluator.check_conditions( - rule["conditions"], uid, display_name - ) + matches = evaluator.check_conditions(rule.conditions, uid, display_name) if matches: - actions = [x for x in rule["actions"] if x != "dont_notify"] + actions = [x for x in rule.actions if x != "dont_notify"] if actions and "notify" in actions: # Push rules say we should notify the user of this event actions_by_user[uid] = actions diff --git a/synapse/push/clientformat.py b/synapse/push/clientformat.py index 5117ef6854..73618d9234 100644 --- a/synapse/push/clientformat.py +++ b/synapse/push/clientformat.py @@ -18,16 +18,15 @@ from typing import Any, Dict, List, Optional from synapse.push.rulekinds import PRIORITY_CLASS_INVERSE_MAP, PRIORITY_CLASS_MAP from synapse.types import UserID +from .baserules import FilteredPushRules, PushRule + def format_push_rules_for_user( - user: UserID, ruleslist: List + user: UserID, ruleslist: FilteredPushRules ) -> Dict[str, Dict[str, list]]: """Converts a list of rawrules and a enabled map into nested dictionaries to match the Matrix client-server format for push rules""" - # We're going to be mutating this a lot, so do a deep copy - ruleslist = copy.deepcopy(ruleslist) - rules: Dict[str, Dict[str, List[Dict[str, Any]]]] = { "global": {}, "device": {}, @@ -35,11 +34,30 @@ def format_push_rules_for_user( rules["global"] = _add_empty_priority_class_arrays(rules["global"]) - for r in ruleslist: - template_name = _priority_class_to_template_name(r["priority_class"]) + for r, enabled in ruleslist: + template_name = _priority_class_to_template_name(r.priority_class) + + rulearray = rules["global"][template_name] + + template_rule = _rule_to_template(r) + if not template_rule: + continue + + rulearray.append(template_rule) + + template_rule["enabled"] = enabled + + if "conditions" not in template_rule: + # Not all formatted rules have explicit conditions, e.g. "room" + # rules omit them as they can be derived from the kind and rule ID. + # + # If the formatted rule has no conditions then we can skip the + # formatting of conditions. + continue # Remove internal stuff. - for c in r["conditions"]: + template_rule["conditions"] = copy.deepcopy(template_rule["conditions"]) + for c in template_rule["conditions"]: c.pop("_cache_key", None) pattern_type = c.pop("pattern_type", None) @@ -52,16 +70,6 @@ def format_push_rules_for_user( if sender_type == "user_id": c["sender"] = user.to_string() - rulearray = rules["global"][template_name] - - template_rule = _rule_to_template(r) - if template_rule: - if "enabled" in r: - template_rule["enabled"] = r["enabled"] - else: - template_rule["enabled"] = True - rulearray.append(template_rule) - return rules @@ -71,24 +79,24 @@ def _add_empty_priority_class_arrays(d: Dict[str, list]) -> Dict[str, list]: return d -def _rule_to_template(rule: Dict[str, Any]) -> Optional[Dict[str, Any]]: - unscoped_rule_id = None - if "rule_id" in rule: - unscoped_rule_id = _rule_id_from_namespaced(rule["rule_id"]) +def _rule_to_template(rule: PushRule) -> Optional[Dict[str, Any]]: + templaterule: Dict[str, Any] + + unscoped_rule_id = _rule_id_from_namespaced(rule.rule_id) - template_name = _priority_class_to_template_name(rule["priority_class"]) + template_name = _priority_class_to_template_name(rule.priority_class) if template_name in ["override", "underride"]: - templaterule = {k: rule[k] for k in ["conditions", "actions"]} + templaterule = {"conditions": rule.conditions, "actions": rule.actions} elif template_name in ["sender", "room"]: - templaterule = {"actions": rule["actions"]} - unscoped_rule_id = rule["conditions"][0]["pattern"] + templaterule = {"actions": rule.actions} + unscoped_rule_id = rule.conditions[0]["pattern"] elif template_name == "content": - if len(rule["conditions"]) != 1: + if len(rule.conditions) != 1: return None - thecond = rule["conditions"][0] + thecond = rule.conditions[0] if "pattern" not in thecond: return None - templaterule = {"actions": rule["actions"]} + templaterule = {"actions": rule.actions} templaterule["pattern"] = thecond["pattern"] else: # This should not be reached unless this function is not kept in sync @@ -97,8 +105,8 @@ def _rule_to_template(rule: Dict[str, Any]) -> Optional[Dict[str, Any]]: if unscoped_rule_id: templaterule["rule_id"] = unscoped_rule_id - if "default" in rule: - templaterule["default"] = rule["default"] + if rule.default: + templaterule["default"] = True return templaterule diff --git a/synapse/push/push_rule_evaluator.py b/synapse/push/push_rule_evaluator.py index 2e8a017add..3c5632cd91 100644 --- a/synapse/push/push_rule_evaluator.py +++ b/synapse/push/push_rule_evaluator.py @@ -15,7 +15,18 @@ import logging import re -from typing import Any, Dict, List, Mapping, Optional, Pattern, Set, Tuple, Union +from typing import ( + Any, + Dict, + List, + Mapping, + Optional, + Pattern, + Sequence, + Set, + Tuple, + Union, +) from matrix_common.regex import glob_to_regex, to_word_pattern @@ -32,14 +43,14 @@ INEQUALITY_EXPR = re.compile("^([=<>]*)([0-9]*)$") def _room_member_count( - ev: EventBase, condition: Dict[str, Any], room_member_count: int + ev: EventBase, condition: Mapping[str, Any], room_member_count: int ) -> bool: return _test_ineq_condition(condition, room_member_count) def _sender_notification_permission( ev: EventBase, - condition: Dict[str, Any], + condition: Mapping[str, Any], sender_power_level: int, power_levels: Dict[str, Union[int, Dict[str, int]]], ) -> bool: @@ -54,7 +65,7 @@ def _sender_notification_permission( return sender_power_level >= room_notif_level -def _test_ineq_condition(condition: Dict[str, Any], number: int) -> bool: +def _test_ineq_condition(condition: Mapping[str, Any], number: int) -> bool: if "is" not in condition: return False m = INEQUALITY_EXPR.match(condition["is"]) @@ -137,7 +148,7 @@ class PushRuleEvaluatorForEvent: self._condition_cache: Dict[str, bool] = {} def check_conditions( - self, conditions: List[dict], uid: str, display_name: Optional[str] + self, conditions: Sequence[Mapping], uid: str, display_name: Optional[str] ) -> bool: """ Returns true if a user's conditions/user ID/display name match the event. @@ -169,7 +180,7 @@ class PushRuleEvaluatorForEvent: return True def matches( - self, condition: Dict[str, Any], user_id: str, display_name: Optional[str] + self, condition: Mapping[str, Any], user_id: str, display_name: Optional[str] ) -> bool: """ Returns true if a user's condition/user ID/display name match the event. @@ -204,7 +215,7 @@ class PushRuleEvaluatorForEvent: # endpoint with an unknown kind, see _rule_tuple_from_request_object. return True - def _event_match(self, condition: dict, user_id: str) -> bool: + def _event_match(self, condition: Mapping, user_id: str) -> bool: """ Check an "event_match" push rule condition. @@ -269,7 +280,7 @@ class PushRuleEvaluatorForEvent: return bool(r.search(body)) - def _relation_match(self, condition: dict, user_id: str) -> bool: + def _relation_match(self, condition: Mapping, user_id: str) -> bool: """ Check an "relation_match" push rule condition. diff --git a/synapse/replication/slave/storage/push_rule.py b/synapse/replication/slave/storage/push_rule.py index 52ee3f7e58..5e65eaf1e0 100644 --- a/synapse/replication/slave/storage/push_rule.py +++ b/synapse/replication/slave/storage/push_rule.py @@ -31,6 +31,5 @@ class SlavedPushRuleStore(SlavedEventStore, PushRulesWorkerStore): self._push_rules_stream_id_gen.advance(instance_name, token) for row in rows: self.get_push_rules_for_user.invalidate((row.user_id,)) - self.get_push_rules_enabled_for_user.invalidate((row.user_id,)) self.push_rules_stream_cache.entity_has_changed(row.user_id, token) return super().process_replication_rows(stream_name, instance_name, token, rows) diff --git a/synapse/rest/admin/_base.py b/synapse/rest/admin/_base.py index 399b205aaf..b467a61dfb 100644 --- a/synapse/rest/admin/_base.py +++ b/synapse/rest/admin/_base.py @@ -19,7 +19,7 @@ from typing import Iterable, Pattern from synapse.api.auth import Auth from synapse.api.errors import AuthError from synapse.http.site import SynapseRequest -from synapse.types import UserID +from synapse.types import Requester def admin_patterns(path_regex: str, version: str = "v1") -> Iterable[Pattern]: @@ -48,19 +48,19 @@ async def assert_requester_is_admin(auth: Auth, request: SynapseRequest) -> None AuthError if the requester is not a server admin """ requester = await auth.get_user_by_req(request) - await assert_user_is_admin(auth, requester.user) + await assert_user_is_admin(auth, requester) -async def assert_user_is_admin(auth: Auth, user_id: UserID) -> None: +async def assert_user_is_admin(auth: Auth, requester: Requester) -> None: """Verify that the given user is an admin user Args: auth: Auth singleton - user_id: user to check + requester: The user making the request, according to the access token. Raises: AuthError if the user is not a server admin """ - is_admin = await auth.is_server_admin(user_id) + is_admin = await auth.is_server_admin(requester) if not is_admin: raise AuthError(HTTPStatus.FORBIDDEN, "You are not a server admin") diff --git a/synapse/rest/admin/media.py b/synapse/rest/admin/media.py index 19d4a008e8..73470f09ae 100644 --- a/synapse/rest/admin/media.py +++ b/synapse/rest/admin/media.py @@ -54,7 +54,7 @@ class QuarantineMediaInRoom(RestServlet): self, request: SynapseRequest, room_id: str ) -> Tuple[int, JsonDict]: requester = await self.auth.get_user_by_req(request) - await assert_user_is_admin(self.auth, requester.user) + await assert_user_is_admin(self.auth, requester) logging.info("Quarantining room: %s", room_id) @@ -81,7 +81,7 @@ class QuarantineMediaByUser(RestServlet): self, request: SynapseRequest, user_id: str ) -> Tuple[int, JsonDict]: requester = await self.auth.get_user_by_req(request) - await assert_user_is_admin(self.auth, requester.user) + await assert_user_is_admin(self.auth, requester) logging.info("Quarantining media by user: %s", user_id) @@ -110,7 +110,7 @@ class QuarantineMediaByID(RestServlet): self, request: SynapseRequest, server_name: str, media_id: str ) -> Tuple[int, JsonDict]: requester = await self.auth.get_user_by_req(request) - await assert_user_is_admin(self.auth, requester.user) + await assert_user_is_admin(self.auth, requester) logging.info("Quarantining media by ID: %s/%s", server_name, media_id) diff --git a/synapse/rest/admin/rooms.py b/synapse/rest/admin/rooms.py index 9d953d58de..3d870629c4 100644 --- a/synapse/rest/admin/rooms.py +++ b/synapse/rest/admin/rooms.py @@ -75,7 +75,7 @@ class RoomRestV2Servlet(RestServlet): ) -> Tuple[int, JsonDict]: requester = await self._auth.get_user_by_req(request) - await assert_user_is_admin(self._auth, requester.user) + await assert_user_is_admin(self._auth, requester) content = parse_json_object_from_request(request) @@ -303,6 +303,7 @@ class RoomRestServlet(RestServlet): members = await self.store.get_users_in_room(room_id) ret["joined_local_devices"] = await self.store.count_devices_by_users(members) + ret["forgotten"] = await self.store.is_locally_forgotten_room(room_id) return HTTPStatus.OK, ret @@ -326,7 +327,7 @@ class RoomRestServlet(RestServlet): pagination_handler: "PaginationHandler", ) -> Tuple[int, JsonDict]: requester = await auth.get_user_by_req(request) - await assert_user_is_admin(auth, requester.user) + await assert_user_is_admin(auth, requester) content = parse_json_object_from_request(request) @@ -460,7 +461,7 @@ class JoinRoomAliasServlet(ResolveRoomIdMixin, RestServlet): assert request.args is not None requester = await self.auth.get_user_by_req(request) - await assert_user_is_admin(self.auth, requester.user) + await assert_user_is_admin(self.auth, requester) content = parse_json_object_from_request(request) @@ -550,7 +551,7 @@ class MakeRoomAdminRestServlet(ResolveRoomIdMixin, RestServlet): self, request: SynapseRequest, room_identifier: str ) -> Tuple[int, JsonDict]: requester = await self.auth.get_user_by_req(request) - await assert_user_is_admin(self.auth, requester.user) + await assert_user_is_admin(self.auth, requester) content = parse_json_object_from_request(request, allow_empty_body=True) room_id, _ = await self.resolve_room_id(room_identifier) @@ -741,7 +742,7 @@ class RoomEventContextServlet(RestServlet): self, request: SynapseRequest, room_id: str, event_id: str ) -> Tuple[int, JsonDict]: requester = await self.auth.get_user_by_req(request, allow_guest=False) - await assert_user_is_admin(self.auth, requester.user) + await assert_user_is_admin(self.auth, requester) limit = parse_integer(request, "limit", default=10) @@ -833,7 +834,7 @@ class BlockRoomRestServlet(RestServlet): self, request: SynapseRequest, room_id: str ) -> Tuple[int, JsonDict]: requester = await self._auth.get_user_by_req(request) - await assert_user_is_admin(self._auth, requester.user) + await assert_user_is_admin(self._auth, requester) content = parse_json_object_from_request(request) diff --git a/synapse/rest/admin/users.py b/synapse/rest/admin/users.py index ba2f7fa6d8..78ee9b6532 100644 --- a/synapse/rest/admin/users.py +++ b/synapse/rest/admin/users.py @@ -183,7 +183,7 @@ class UserRestServletV2(RestServlet): self, request: SynapseRequest, user_id: str ) -> Tuple[int, JsonDict]: requester = await self.auth.get_user_by_req(request) - await assert_user_is_admin(self.auth, requester.user) + await assert_user_is_admin(self.auth, requester) target_user = UserID.from_string(user_id) body = parse_json_object_from_request(request) @@ -575,10 +575,9 @@ class WhoisRestServlet(RestServlet): ) -> Tuple[int, JsonDict]: target_user = UserID.from_string(user_id) requester = await self.auth.get_user_by_req(request) - auth_user = requester.user - if target_user != auth_user: - await assert_user_is_admin(self.auth, auth_user) + if target_user != requester.user: + await assert_user_is_admin(self.auth, requester) if not self.is_mine(target_user): raise SynapseError(HTTPStatus.BAD_REQUEST, "Can only whois a local user") @@ -601,7 +600,7 @@ class DeactivateAccountRestServlet(RestServlet): self, request: SynapseRequest, target_user_id: str ) -> Tuple[int, JsonDict]: requester = await self.auth.get_user_by_req(request) - await assert_user_is_admin(self.auth, requester.user) + await assert_user_is_admin(self.auth, requester) if not self.is_mine(UserID.from_string(target_user_id)): raise SynapseError( @@ -693,7 +692,7 @@ class ResetPasswordRestServlet(RestServlet): This needs user to have administrator access in Synapse. """ requester = await self.auth.get_user_by_req(request) - await assert_user_is_admin(self.auth, requester.user) + await assert_user_is_admin(self.auth, requester) UserID.from_string(target_user_id) @@ -807,7 +806,7 @@ class UserAdminServlet(RestServlet): self, request: SynapseRequest, user_id: str ) -> Tuple[int, JsonDict]: requester = await self.auth.get_user_by_req(request) - await assert_user_is_admin(self.auth, requester.user) + await assert_user_is_admin(self.auth, requester) auth_user = requester.user target_user = UserID.from_string(user_id) @@ -921,7 +920,7 @@ class UserTokenRestServlet(RestServlet): self, request: SynapseRequest, user_id: str ) -> Tuple[int, JsonDict]: requester = await self.auth.get_user_by_req(request) - await assert_user_is_admin(self.auth, requester.user) + await assert_user_is_admin(self.auth, requester) auth_user = requester.user if not self.is_mine_id(user_id): diff --git a/synapse/rest/client/account.py b/synapse/rest/client/account.py index 50edc6b7d3..1f9a8ccc23 100644 --- a/synapse/rest/client/account.py +++ b/synapse/rest/client/account.py @@ -15,10 +15,11 @@ # limitations under the License. import logging import random -from http import HTTPStatus from typing import TYPE_CHECKING, Optional, Tuple from urllib.parse import urlparse +from pydantic import StrictBool, StrictStr, constr + from twisted.web.server import Request from synapse.api.constants import LoginType @@ -28,18 +29,20 @@ from synapse.api.errors import ( SynapseError, ThreepidValidationError, ) -from synapse.config.emailconfig import ThreepidBehaviour from synapse.handlers.ui_auth import UIAuthSessionDataConstants from synapse.http.server import HttpServer, finish_request, respond_with_html from synapse.http.servlet import ( RestServlet, assert_params_in_dict, + parse_and_validate_json_object_from_request, parse_json_object_from_request, parse_string, ) from synapse.http.site import SynapseRequest from synapse.metrics import threepid_send_requests from synapse.push.mailer import Mailer +from synapse.rest.client.models import AuthenticationData, EmailRequestTokenBody +from synapse.rest.models import RequestBodyModel from synapse.types import JsonDict from synapse.util.msisdn import phone_number_to_msisdn from synapse.util.stringutils import assert_valid_client_secret, random_string @@ -64,7 +67,7 @@ class EmailPasswordRequestTokenRestServlet(RestServlet): self.config = hs.config self.identity_handler = hs.get_identity_handler() - if self.config.email.threepid_behaviour_email == ThreepidBehaviour.LOCAL: + if self.config.email.can_verify_email: self.mailer = Mailer( hs=self.hs, app_name=self.config.email.email_app_name, @@ -73,41 +76,24 @@ class EmailPasswordRequestTokenRestServlet(RestServlet): ) async def on_POST(self, request: SynapseRequest) -> Tuple[int, JsonDict]: - if self.config.email.threepid_behaviour_email == ThreepidBehaviour.OFF: - if self.config.email.local_threepid_handling_disabled_due_to_email_config: - logger.warning( - "User password resets have been disabled due to lack of email config" - ) + if not self.config.email.can_verify_email: + logger.warning( + "User password resets have been disabled due to lack of email config" + ) raise SynapseError( 400, "Email-based password resets have been disabled on this server" ) - body = parse_json_object_from_request(request) - - assert_params_in_dict(body, ["client_secret", "email", "send_attempt"]) - - # Extract params from body - client_secret = body["client_secret"] - assert_valid_client_secret(client_secret) - - # Canonicalise the email address. The addresses are all stored canonicalised - # in the database. This allows the user to reset his password without having to - # know the exact spelling (eg. upper and lower case) of address in the database. - # Stored in the database "foo@bar.com" - # User requests with "FOO@bar.com" would raise a Not Found error - try: - email = validate_email(body["email"]) - except ValueError as e: - raise SynapseError(400, str(e)) - send_attempt = body["send_attempt"] - next_link = body.get("next_link") # Optional param + body = parse_and_validate_json_object_from_request( + request, EmailRequestTokenBody + ) - if next_link: + if body.next_link: # Raise if the provided next_link value isn't valid - assert_valid_next_link(self.hs, next_link) + assert_valid_next_link(self.hs, body.next_link) await self.identity_handler.ratelimit_request_token_requests( - request, "email", email + request, "email", body.email ) # The email will be sent to the stored address. @@ -115,7 +101,7 @@ class EmailPasswordRequestTokenRestServlet(RestServlet): # an email address which is controlled by the attacker but which, after # canonicalisation, matches the one in our database. existing_user_id = await self.hs.get_datastores().main.get_user_id_by_threepid( - "email", email + "email", body.email ) if existing_user_id is None: @@ -129,35 +115,20 @@ class EmailPasswordRequestTokenRestServlet(RestServlet): raise SynapseError(400, "Email not found", Codes.THREEPID_NOT_FOUND) - if self.config.email.threepid_behaviour_email == ThreepidBehaviour.REMOTE: - assert self.hs.config.registration.account_threepid_delegate_email - - # Have the configured identity server handle the request - ret = await self.identity_handler.request_email_token( - self.hs.config.registration.account_threepid_delegate_email, - email, - client_secret, - send_attempt, - next_link, - ) - else: - # Send password reset emails from Synapse - sid = await self.identity_handler.send_threepid_validation( - email, - client_secret, - send_attempt, - self.mailer.send_password_reset_mail, - next_link, - ) - - # Wrap the session id in a JSON object - ret = {"sid": sid} - + # Send password reset emails from Synapse + sid = await self.identity_handler.send_threepid_validation( + body.email, + body.client_secret, + body.send_attempt, + self.mailer.send_password_reset_mail, + body.next_link, + ) threepid_send_requests.labels(type="email", reason="password_reset").observe( - send_attempt + body.send_attempt ) - return 200, ret + # Wrap the session id in a JSON object + return 200, {"sid": sid} class PasswordRestServlet(RestServlet): @@ -172,16 +143,23 @@ class PasswordRestServlet(RestServlet): self.password_policy_handler = hs.get_password_policy_handler() self._set_password_handler = hs.get_set_password_handler() + class PostBody(RequestBodyModel): + auth: Optional[AuthenticationData] = None + logout_devices: StrictBool = True + if TYPE_CHECKING: + # workaround for https://github.com/samuelcolvin/pydantic/issues/156 + new_password: Optional[StrictStr] = None + else: + new_password: Optional[constr(max_length=512, strict=True)] = None + @interactive_auth_handler async def on_POST(self, request: SynapseRequest) -> Tuple[int, JsonDict]: - body = parse_json_object_from_request(request) + body = parse_and_validate_json_object_from_request(request, self.PostBody) # we do basic sanity checks here because the auth layer will store these # in sessions. Pull out the new password provided to us. - new_password = body.pop("new_password", None) + new_password = body.new_password if new_password is not None: - if not isinstance(new_password, str) or len(new_password) > 512: - raise SynapseError(400, "Invalid password") self.password_policy_handler.validate_password(new_password) # there are two possibilities here. Either the user does not have an @@ -201,7 +179,7 @@ class PasswordRestServlet(RestServlet): params, session_id = await self.auth_handler.validate_user_via_ui_auth( requester, request, - body, + body.dict(exclude_unset=True), "modify your account password", ) except InteractiveAuthIncompleteError as e: @@ -224,7 +202,7 @@ class PasswordRestServlet(RestServlet): result, params, session_id = await self.auth_handler.check_ui_auth( [[LoginType.EMAIL_IDENTITY]], request, - body, + body.dict(exclude_unset=True), "modify your account password", ) except InteractiveAuthIncompleteError as e: @@ -299,37 +277,33 @@ class DeactivateAccountRestServlet(RestServlet): self.auth_handler = hs.get_auth_handler() self._deactivate_account_handler = hs.get_deactivate_account_handler() + class PostBody(RequestBodyModel): + auth: Optional[AuthenticationData] = None + id_server: Optional[StrictStr] = None + # Not specced, see https://github.com/matrix-org/matrix-spec/issues/297 + erase: StrictBool = False + @interactive_auth_handler async def on_POST(self, request: SynapseRequest) -> Tuple[int, JsonDict]: - body = parse_json_object_from_request(request) - erase = body.get("erase", False) - if not isinstance(erase, bool): - raise SynapseError( - HTTPStatus.BAD_REQUEST, - "Param 'erase' must be a boolean, if given", - Codes.BAD_JSON, - ) + body = parse_and_validate_json_object_from_request(request, self.PostBody) requester = await self.auth.get_user_by_req(request) # allow ASes to deactivate their own users if requester.app_service: await self._deactivate_account_handler.deactivate_account( - requester.user.to_string(), erase, requester + requester.user.to_string(), body.erase, requester ) return 200, {} await self.auth_handler.validate_user_via_ui_auth( requester, request, - body, + body.dict(exclude_unset=True), "deactivate your account", ) result = await self._deactivate_account_handler.deactivate_account( - requester.user.to_string(), - erase, - requester, - id_server=body.get("id_server"), + requester.user.to_string(), body.erase, requester, id_server=body.id_server ) if result: id_server_unbind_result = "success" @@ -349,7 +323,7 @@ class EmailThreepidRequestTokenRestServlet(RestServlet): self.identity_handler = hs.get_identity_handler() self.store = self.hs.get_datastores().main - if self.config.email.threepid_behaviour_email == ThreepidBehaviour.LOCAL: + if self.config.email.can_verify_email: self.mailer = Mailer( hs=self.hs, app_name=self.config.email.email_app_name, @@ -358,34 +332,20 @@ class EmailThreepidRequestTokenRestServlet(RestServlet): ) async def on_POST(self, request: SynapseRequest) -> Tuple[int, JsonDict]: - if self.config.email.threepid_behaviour_email == ThreepidBehaviour.OFF: - if self.config.email.local_threepid_handling_disabled_due_to_email_config: - logger.warning( - "Adding emails have been disabled due to lack of an email config" - ) + if not self.config.email.can_verify_email: + logger.warning( + "Adding emails have been disabled due to lack of an email config" + ) raise SynapseError( - 400, "Adding an email to your account is disabled on this server" + 400, + "Adding an email to your account is disabled on this server", ) - body = parse_json_object_from_request(request) - assert_params_in_dict(body, ["client_secret", "email", "send_attempt"]) - client_secret = body["client_secret"] - assert_valid_client_secret(client_secret) - - # Canonicalise the email address. The addresses are all stored canonicalised - # in the database. - # This ensures that the validation email is sent to the canonicalised address - # as it will later be entered into the database. - # Otherwise the email will be sent to "FOO@bar.com" and stored as - # "foo@bar.com" in database. - try: - email = validate_email(body["email"]) - except ValueError as e: - raise SynapseError(400, str(e)) - send_attempt = body["send_attempt"] - next_link = body.get("next_link") # Optional param + body = parse_and_validate_json_object_from_request( + request, EmailRequestTokenBody + ) - if not await check_3pid_allowed(self.hs, "email", email): + if not await check_3pid_allowed(self.hs, "email", body.email): raise SynapseError( 403, "Your email domain is not authorized on this server", @@ -393,14 +353,14 @@ class EmailThreepidRequestTokenRestServlet(RestServlet): ) await self.identity_handler.ratelimit_request_token_requests( - request, "email", email + request, "email", body.email ) - if next_link: + if body.next_link: # Raise if the provided next_link value isn't valid - assert_valid_next_link(self.hs, next_link) + assert_valid_next_link(self.hs, body.next_link) - existing_user_id = await self.store.get_user_id_by_threepid("email", email) + existing_user_id = await self.store.get_user_id_by_threepid("email", body.email) if existing_user_id is not None: if self.config.server.request_token_inhibit_3pid_errors: @@ -413,35 +373,21 @@ class EmailThreepidRequestTokenRestServlet(RestServlet): raise SynapseError(400, "Email is already in use", Codes.THREEPID_IN_USE) - if self.config.email.threepid_behaviour_email == ThreepidBehaviour.REMOTE: - assert self.hs.config.registration.account_threepid_delegate_email - - # Have the configured identity server handle the request - ret = await self.identity_handler.request_email_token( - self.hs.config.registration.account_threepid_delegate_email, - email, - client_secret, - send_attempt, - next_link, - ) - else: - # Send threepid validation emails from Synapse - sid = await self.identity_handler.send_threepid_validation( - email, - client_secret, - send_attempt, - self.mailer.send_add_threepid_mail, - next_link, - ) - - # Wrap the session id in a JSON object - ret = {"sid": sid} + # Send threepid validation emails from Synapse + sid = await self.identity_handler.send_threepid_validation( + body.email, + body.client_secret, + body.send_attempt, + self.mailer.send_add_threepid_mail, + body.next_link, + ) threepid_send_requests.labels(type="email", reason="add_threepid").observe( - send_attempt + body.send_attempt ) - return 200, ret + # Wrap the session id in a JSON object + return 200, {"sid": sid} class MsisdnThreepidRequestTokenRestServlet(RestServlet): @@ -534,24 +480,18 @@ class AddThreepidEmailSubmitTokenServlet(RestServlet): self.config = hs.config self.clock = hs.get_clock() self.store = hs.get_datastores().main - if self.config.email.threepid_behaviour_email == ThreepidBehaviour.LOCAL: + if self.config.email.can_verify_email: self._failure_email_template = ( self.config.email.email_add_threepid_template_failure_html ) async def on_GET(self, request: Request) -> None: - if self.config.email.threepid_behaviour_email == ThreepidBehaviour.OFF: - if self.config.email.local_threepid_handling_disabled_due_to_email_config: - logger.warning( - "Adding emails have been disabled due to lack of an email config" - ) - raise SynapseError( - 400, "Adding an email to your account is disabled on this server" + if not self.config.email.can_verify_email: + logger.warning( + "Adding emails have been disabled due to lack of an email config" ) - elif self.config.email.threepid_behaviour_email == ThreepidBehaviour.REMOTE: raise SynapseError( - 400, - "This homeserver is not validating threepids.", + 400, "Adding an email to your account is disabled on this server" ) sid = parse_string(request, "sid", required=True) diff --git a/synapse/rest/client/devices.py b/synapse/rest/client/devices.py index 6fab102437..ed6ce78d47 100644 --- a/synapse/rest/client/devices.py +++ b/synapse/rest/client/devices.py @@ -42,12 +42,26 @@ class DevicesRestServlet(RestServlet): self.hs = hs self.auth = hs.get_auth() self.device_handler = hs.get_device_handler() + self._msc3852_enabled = hs.config.experimental.msc3852_enabled async def on_GET(self, request: SynapseRequest) -> Tuple[int, JsonDict]: requester = await self.auth.get_user_by_req(request, allow_guest=True) devices = await self.device_handler.get_devices_by_user( requester.user.to_string() ) + + # If MSC3852 is disabled, then the "last_seen_user_agent" field will be + # removed from each device. If it is enabled, then the field name will + # be replaced by the unstable identifier. + # + # When MSC3852 is accepted, this block of code can just be removed to + # expose "last_seen_user_agent" to clients. + for device in devices: + last_seen_user_agent = device["last_seen_user_agent"] + del device["last_seen_user_agent"] + if self._msc3852_enabled: + device["org.matrix.msc3852.last_seen_user_agent"] = last_seen_user_agent + return 200, {"devices": devices} @@ -108,6 +122,7 @@ class DeviceRestServlet(RestServlet): self.auth = hs.get_auth() self.device_handler = hs.get_device_handler() self.auth_handler = hs.get_auth_handler() + self._msc3852_enabled = hs.config.experimental.msc3852_enabled async def on_GET( self, request: SynapseRequest, device_id: str @@ -118,6 +133,18 @@ class DeviceRestServlet(RestServlet): ) if device is None: raise NotFoundError("No device found") + + # If MSC3852 is disabled, then the "last_seen_user_agent" field will be + # removed from each device. If it is enabled, then the field name will + # be replaced by the unstable identifier. + # + # When MSC3852 is accepted, this block of code can just be removed to + # expose "last_seen_user_agent" to clients. + last_seen_user_agent = device["last_seen_user_agent"] + del device["last_seen_user_agent"] + if self._msc3852_enabled: + device["org.matrix.msc3852.last_seen_user_agent"] = last_seen_user_agent + return 200, device @interactive_auth_handler diff --git a/synapse/rest/client/keys.py b/synapse/rest/client/keys.py index e3f454896a..a395694fa5 100644 --- a/synapse/rest/client/keys.py +++ b/synapse/rest/client/keys.py @@ -26,7 +26,7 @@ from synapse.http.servlet import ( parse_string, ) from synapse.http.site import SynapseRequest -from synapse.logging.opentracing import log_kv, set_tag, trace_with_opname +from synapse.logging.opentracing import log_kv, set_tag from synapse.types import JsonDict, StreamToken from ._base import client_patterns, interactive_auth_handler @@ -71,7 +71,6 @@ class KeyUploadServlet(RestServlet): self.e2e_keys_handler = hs.get_e2e_keys_handler() self.device_handler = hs.get_device_handler() - @trace_with_opname("upload_keys") async def on_POST( self, request: SynapseRequest, device_id: Optional[str] ) -> Tuple[int, JsonDict]: diff --git a/synapse/rest/client/models.py b/synapse/rest/client/models.py new file mode 100644 index 0000000000..3150602997 --- /dev/null +++ b/synapse/rest/client/models.py @@ -0,0 +1,69 @@ +# Copyright 2022 The Matrix.org Foundation C.I.C. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +from typing import TYPE_CHECKING, Dict, Optional + +from pydantic import Extra, StrictInt, StrictStr, constr, validator + +from synapse.rest.models import RequestBodyModel +from synapse.util.threepids import validate_email + + +class AuthenticationData(RequestBodyModel): + """ + Data used during user-interactive authentication. + + (The name "Authentication Data" is taken directly from the spec.) + + Additional keys will be present, depending on the `type` field. Use `.dict()` to + access them. + """ + + class Config: + extra = Extra.allow + + session: Optional[StrictStr] = None + type: Optional[StrictStr] = None + + +class EmailRequestTokenBody(RequestBodyModel): + if TYPE_CHECKING: + client_secret: StrictStr + else: + # See also assert_valid_client_secret() + client_secret: constr( + regex="[0-9a-zA-Z.=_-]", # noqa: F722 + min_length=0, + max_length=255, + strict=True, + ) + email: StrictStr + id_server: Optional[StrictStr] + id_access_token: Optional[StrictStr] + next_link: Optional[StrictStr] + send_attempt: StrictInt + + @validator("id_access_token", always=True) + def token_required_for_identity_server( + cls, token: Optional[str], values: Dict[str, object] + ) -> Optional[str]: + if values.get("id_server") is not None and token is None: + raise ValueError("id_access_token is required if an id_server is supplied.") + return token + + # Canonicalise the email address. The addresses are all stored canonicalised + # in the database. This allows the user to reset his password without having to + # know the exact spelling (eg. upper and lower case) of address in the database. + # Without this, an email stored in the database as "foo@bar.com" would cause + # user requests for "FOO@bar.com" to raise a Not Found error. + _email_validator = validator("email", allow_reuse=True)(validate_email) diff --git a/synapse/rest/client/profile.py b/synapse/rest/client/profile.py index c16d707909..e69fa0829d 100644 --- a/synapse/rest/client/profile.py +++ b/synapse/rest/client/profile.py @@ -66,7 +66,7 @@ class ProfileDisplaynameRestServlet(RestServlet): ) -> Tuple[int, JsonDict]: requester = await self.auth.get_user_by_req(request, allow_guest=True) user = UserID.from_string(user_id) - is_admin = await self.auth.is_server_admin(requester.user) + is_admin = await self.auth.is_server_admin(requester) content = parse_json_object_from_request(request) @@ -123,7 +123,7 @@ class ProfileAvatarURLRestServlet(RestServlet): ) -> Tuple[int, JsonDict]: requester = await self.auth.get_user_by_req(request) user = UserID.from_string(user_id) - is_admin = await self.auth.is_server_admin(requester.user) + is_admin = await self.auth.is_server_admin(requester) content = parse_json_object_from_request(request) try: diff --git a/synapse/rest/client/register.py b/synapse/rest/client/register.py index 956c45e60a..20bab20c8f 100644 --- a/synapse/rest/client/register.py +++ b/synapse/rest/client/register.py @@ -31,7 +31,6 @@ from synapse.api.errors import ( ) from synapse.api.ratelimiting import Ratelimiter from synapse.config import ConfigError -from synapse.config.emailconfig import ThreepidBehaviour from synapse.config.homeserver import HomeServerConfig from synapse.config.ratelimiting import FederationRatelimitSettings from synapse.config.server import is_threepid_reserved @@ -74,7 +73,7 @@ class EmailRegisterRequestTokenRestServlet(RestServlet): self.identity_handler = hs.get_identity_handler() self.config = hs.config - if self.hs.config.email.threepid_behaviour_email == ThreepidBehaviour.LOCAL: + if self.hs.config.email.can_verify_email: self.mailer = Mailer( hs=self.hs, app_name=self.config.email.email_app_name, @@ -83,13 +82,10 @@ class EmailRegisterRequestTokenRestServlet(RestServlet): ) async def on_POST(self, request: SynapseRequest) -> Tuple[int, JsonDict]: - if self.hs.config.email.threepid_behaviour_email == ThreepidBehaviour.OFF: - if ( - self.hs.config.email.local_threepid_handling_disabled_due_to_email_config - ): - logger.warning( - "Email registration has been disabled due to lack of email config" - ) + if not self.hs.config.email.can_verify_email: + logger.warning( + "Email registration has been disabled due to lack of email config" + ) raise SynapseError( 400, "Email-based registration has been disabled on this server" ) @@ -138,35 +134,21 @@ class EmailRegisterRequestTokenRestServlet(RestServlet): raise SynapseError(400, "Email is already in use", Codes.THREEPID_IN_USE) - if self.config.email.threepid_behaviour_email == ThreepidBehaviour.REMOTE: - assert self.hs.config.registration.account_threepid_delegate_email - - # Have the configured identity server handle the request - ret = await self.identity_handler.request_email_token( - self.hs.config.registration.account_threepid_delegate_email, - email, - client_secret, - send_attempt, - next_link, - ) - else: - # Send registration emails from Synapse, - # wrapping the session id in a JSON object. - ret = { - "sid": await self.identity_handler.send_threepid_validation( - email, - client_secret, - send_attempt, - self.mailer.send_registration_mail, - next_link, - ) - } + # Send registration emails from Synapse + sid = await self.identity_handler.send_threepid_validation( + email, + client_secret, + send_attempt, + self.mailer.send_registration_mail, + next_link, + ) threepid_send_requests.labels(type="email", reason="register").observe( send_attempt ) - return 200, ret + # Wrap the session id in a JSON object + return 200, {"sid": sid} class MsisdnRegisterRequestTokenRestServlet(RestServlet): @@ -260,7 +242,7 @@ class RegistrationSubmitTokenServlet(RestServlet): self.clock = hs.get_clock() self.store = hs.get_datastores().main - if self.config.email.threepid_behaviour_email == ThreepidBehaviour.LOCAL: + if self.config.email.can_verify_email: self._failure_email_template = ( self.config.email.email_registration_template_failure_html ) @@ -270,11 +252,10 @@ class RegistrationSubmitTokenServlet(RestServlet): raise SynapseError( 400, "This medium is currently not supported for registration" ) - if self.config.email.threepid_behaviour_email == ThreepidBehaviour.OFF: - if self.config.email.local_threepid_handling_disabled_due_to_email_config: - logger.warning( - "User registration via email has been disabled due to lack of email config" - ) + if not self.config.email.can_verify_email: + logger.warning( + "User registration via email has been disabled due to lack of email config" + ) raise SynapseError( 400, "Email-based registration is disabled on this server" ) @@ -484,9 +465,6 @@ class RegisterRestServlet(RestServlet): "Appservice token must be provided when using a type of m.login.application_service", ) - # Verify the AS - self.auth.get_appservice_by_req(request) - # Set the desired user according to the AS API (which uses the # 'user' key not 'username'). Since this is a new addition, we'll # fallback to 'username' if they gave one. diff --git a/synapse/rest/client/room.py b/synapse/rest/client/room.py index 2f513164cb..3259de4802 100644 --- a/synapse/rest/client/room.py +++ b/synapse/rest/client/room.py @@ -16,9 +16,12 @@ """ This module contains REST servlets to do with rooms: /rooms/<paths> """ import logging import re +from enum import Enum from typing import TYPE_CHECKING, Awaitable, Dict, List, Optional, Tuple from urllib import parse as urlparse +from prometheus_client.core import Histogram + from twisted.web.server import Request from synapse import event_auth @@ -46,6 +49,7 @@ from synapse.http.servlet import ( parse_strings_from_args, ) from synapse.http.site import SynapseRequest +from synapse.logging.context import make_deferred_yieldable, run_in_background from synapse.logging.opentracing import set_tag from synapse.rest.client._base import client_patterns from synapse.rest.client.transactions import HttpTransactionCache @@ -61,6 +65,70 @@ if TYPE_CHECKING: logger = logging.getLogger(__name__) +class _RoomSize(Enum): + """ + Enum to differentiate sizes of rooms. This is a pretty good approximation + about how hard it will be to get events in the room. We could also look at + room "complexity". + """ + + # This doesn't necessarily mean the room is a DM, just that there is a DM + # amount of people there. + DM_SIZE = "direct_message_size" + SMALL = "small" + SUBSTANTIAL = "substantial" + LARGE = "large" + + @staticmethod + def from_member_count(member_count: int) -> "_RoomSize": + if member_count <= 2: + return _RoomSize.DM_SIZE + elif member_count < 100: + return _RoomSize.SMALL + elif member_count < 1000: + return _RoomSize.SUBSTANTIAL + else: + return _RoomSize.LARGE + + +# This is an extra metric on top of `synapse_http_server_response_time_seconds` +# which times the same sort of thing but this one allows us to see values +# greater than 10s. We use a separate dedicated histogram with its own buckets +# so that we don't increase the cardinality of the general one because it's +# multiplied across hundreds of servlets. +messsages_response_timer = Histogram( + "synapse_room_message_list_rest_servlet_response_time_seconds", + "sec", + # We have a label for room size so we can try to see a more realistic + # picture of /messages response time for bigger rooms. We don't want the + # tiny rooms that can always respond fast skewing our results when we're trying + # to optimize the bigger cases. + ["room_size"], + buckets=( + 0.005, + 0.01, + 0.025, + 0.05, + 0.1, + 0.25, + 0.5, + 1.0, + 2.5, + 5.0, + 10.0, + 20.0, + 30.0, + 60.0, + 80.0, + 100.0, + 120.0, + 150.0, + 180.0, + "+Inf", + ), +) + + class TransactionRestServlet(RestServlet): def __init__(self, hs: "HomeServer"): super().__init__() @@ -165,7 +233,7 @@ class RoomStateEventRestServlet(TransactionRestServlet): msg_handler = self.message_handler data = await msg_handler.get_room_data( - user_id=requester.user.to_string(), + requester=requester, room_id=room_id, event_type=event_type, state_key=state_key, @@ -510,7 +578,7 @@ class RoomMemberListRestServlet(RestServlet): events = await handler.get_state_events( room_id=room_id, - user_id=requester.user.to_string(), + requester=requester, at_token=at_token, state_filter=StateFilter.from_types([(EventTypes.Member, None)]), ) @@ -556,6 +624,7 @@ class RoomMessageListRestServlet(RestServlet): def __init__(self, hs: "HomeServer"): super().__init__() self._hs = hs + self.clock = hs.get_clock() self.pagination_handler = hs.get_pagination_handler() self.auth = hs.get_auth() self.store = hs.get_datastores().main @@ -563,6 +632,18 @@ class RoomMessageListRestServlet(RestServlet): async def on_GET( self, request: SynapseRequest, room_id: str ) -> Tuple[int, JsonDict]: + processing_start_time = self.clock.time_msec() + # Fire off and hope that we get a result by the end. + # + # We're using the mypy type ignore comment because the `@cached` + # decorator on `get_number_joined_users_in_room` doesn't play well with + # the type system. Maybe in the future, it can use some ParamSpec + # wizardry to fix it up. + room_member_count_deferred = run_in_background( # type: ignore[call-arg] + self.store.get_number_joined_users_in_room, + room_id, # type: ignore[arg-type] + ) + requester = await self.auth.get_user_by_req(request, allow_guest=True) pagination_config = await PaginationConfig.from_request( self.store, request, default_limit=10 @@ -593,6 +674,12 @@ class RoomMessageListRestServlet(RestServlet): event_filter=event_filter, ) + processing_end_time = self.clock.time_msec() + room_member_count = await make_deferred_yieldable(room_member_count_deferred) + messsages_response_timer.labels( + room_size=_RoomSize.from_member_count(room_member_count) + ).observe((processing_end_time - processing_start_time) / 1000) + return 200, msgs @@ -613,8 +700,7 @@ class RoomStateRestServlet(RestServlet): # Get all the current state for this room events = await self.message_handler.get_state_events( room_id=room_id, - user_id=requester.user.to_string(), - is_guest=requester.is_guest, + requester=requester, ) return 200, events @@ -672,7 +758,7 @@ class RoomEventServlet(RestServlet): == "true" ) if include_unredacted_content and not await self.auth.is_server_admin( - requester.user + requester ): power_level_event = ( await self._storage_controllers.state.get_current_state_event( @@ -1177,9 +1263,7 @@ class TimestampLookupRestServlet(RestServlet): self, request: SynapseRequest, room_id: str ) -> Tuple[int, JsonDict]: requester = await self._auth.get_user_by_req(request) - await self._auth.check_user_in_room_or_world_readable( - room_id, requester.user.to_string() - ) + await self._auth.check_user_in_room_or_world_readable(room_id, requester) timestamp = parse_integer(request, "ts", required=True) direction = parse_string(request, "dir", default="f", allowed_values=["f", "b"]) diff --git a/synapse/rest/client/sendtodevice.py b/synapse/rest/client/sendtodevice.py index 1a8e9a96d4..46a8b03829 100644 --- a/synapse/rest/client/sendtodevice.py +++ b/synapse/rest/client/sendtodevice.py @@ -19,7 +19,7 @@ from synapse.http import servlet from synapse.http.server import HttpServer from synapse.http.servlet import assert_params_in_dict, parse_json_object_from_request from synapse.http.site import SynapseRequest -from synapse.logging.opentracing import set_tag, trace_with_opname +from synapse.logging.opentracing import set_tag from synapse.rest.client.transactions import HttpTransactionCache from synapse.types import JsonDict @@ -43,7 +43,6 @@ class SendToDeviceRestServlet(servlet.RestServlet): self.txns = HttpTransactionCache(hs) self.device_message_handler = hs.get_device_message_handler() - @trace_with_opname("sendToDevice") def on_PUT( self, request: SynapseRequest, message_type: str, txn_id: str ) -> Awaitable[Tuple[int, JsonDict]]: diff --git a/synapse/rest/models.py b/synapse/rest/models.py new file mode 100644 index 0000000000..ac39cda8e5 --- /dev/null +++ b/synapse/rest/models.py @@ -0,0 +1,23 @@ +from pydantic import BaseModel, Extra + + +class RequestBodyModel(BaseModel): + """A custom version of Pydantic's BaseModel which + + - ignores unknown fields and + - does not allow fields to be overwritten after construction, + + but otherwise uses Pydantic's default behaviour. + + Ignoring unknown fields is a useful default. It means that clients can provide + unstable field not known to the server without the request being refused outright. + + Subclassing in this way is recommended by + https://pydantic-docs.helpmanual.io/usage/model_config/#change-behaviour-globally + """ + + class Config: + # By default, ignore fields that we don't recognise. + extra = Extra.ignore + # By default, don't allow fields to be reassigned after parsing. + allow_mutation = False diff --git a/synapse/rest/synapse/client/password_reset.py b/synapse/rest/synapse/client/password_reset.py index 6ac9dbc7c9..b9402cfb75 100644 --- a/synapse/rest/synapse/client/password_reset.py +++ b/synapse/rest/synapse/client/password_reset.py @@ -17,7 +17,6 @@ from typing import TYPE_CHECKING, Tuple from twisted.web.server import Request from synapse.api.errors import ThreepidValidationError -from synapse.config.emailconfig import ThreepidBehaviour from synapse.http.server import DirectServeHtmlResource from synapse.http.servlet import parse_string from synapse.util.stringutils import assert_valid_client_secret @@ -46,9 +45,6 @@ class PasswordResetSubmitTokenResource(DirectServeHtmlResource): self.clock = hs.get_clock() self.store = hs.get_datastores().main - self._local_threepid_handling_disabled_due_to_email_config = ( - hs.config.email.local_threepid_handling_disabled_due_to_email_config - ) self._confirmation_email_template = ( hs.config.email.email_password_reset_template_confirmation_html ) @@ -59,8 +55,8 @@ class PasswordResetSubmitTokenResource(DirectServeHtmlResource): hs.config.email.email_password_reset_template_failure_html ) - # This resource should not be mounted if threepid behaviour is not LOCAL - assert hs.config.email.threepid_behaviour_email == ThreepidBehaviour.LOCAL + # This resource should only be mounted if email validation is enabled + assert hs.config.email.can_verify_email async def _async_render_GET(self, request: Request) -> Tuple[int, bytes]: sid = parse_string(request, "sid", required=True) diff --git a/synapse/server_notices/server_notices_manager.py b/synapse/server_notices/server_notices_manager.py index 8ecab86ec7..564e3705c2 100644 --- a/synapse/server_notices/server_notices_manager.py +++ b/synapse/server_notices/server_notices_manager.py @@ -102,6 +102,10 @@ class ServerNoticesManager: Returns: The room's ID, or None if no room could be found. """ + # If there is no server notices MXID, then there is no server notices room + if self.server_notices_mxid is None: + return None + rooms = await self._store.get_rooms_for_local_user_where_membership_is( user_id, [Membership.INVITE, Membership.JOIN] ) @@ -111,8 +115,10 @@ class ServerNoticesManager: # be joined. This is kinda deliberate, in that if somebody somehow # manages to invite the system user to a room, that doesn't make it # the server notices room. - user_ids = await self._store.get_users_in_room(room.room_id) - if len(user_ids) <= 2 and self.server_notices_mxid in user_ids: + is_server_notices_room = await self._store.check_local_user_in_room( + user_id=self.server_notices_mxid, room_id=room.room_id + ) + if is_server_notices_room: # we found a room which our user shares with the system notice # user return room.room_id @@ -244,7 +250,7 @@ class ServerNoticesManager: assert self.server_notices_mxid is not None notice_user_data_in_room = await self._message_handler.get_room_data( - self.server_notices_mxid, + create_requester(self.server_notices_mxid), room_id, EventTypes.Member, self.server_notices_mxid, diff --git a/synapse/state/__init__.py b/synapse/state/__init__.py index 140af8bbca..7712fc4c0e 100644 --- a/synapse/state/__init__.py +++ b/synapse/state/__init__.py @@ -44,7 +44,6 @@ from synapse.logging.context import ContextResourceUsage from synapse.replication.http.state import ReplicationUpdateCurrentStateRestServlet from synapse.state import v1, v2 from synapse.storage.databases.main.events_worker import EventRedactBehaviour -from synapse.storage.roommember import ProfileInfo from synapse.storage.state import StateFilter from synapse.types import StateMap from synapse.util.async_helpers import Linearizer @@ -210,11 +209,11 @@ class StateHandler: ret = await self.resolve_state_groups_for_events(room_id, event_ids) return await ret.get_state(self._state_storage_controller, state_filter) - async def get_current_users_in_room( + async def get_current_user_ids_in_room( self, room_id: str, latest_event_ids: List[str] - ) -> Dict[str, ProfileInfo]: + ) -> Set[str]: """ - Get the users who are currently in a room. + Get the users IDs who are currently in a room. Note: This is much slower than using the equivalent method `DataStore.get_users_in_room` or `DataStore.get_users_in_room_with_profiles`, @@ -225,15 +224,15 @@ class StateHandler: room_id: The ID of the room. latest_event_ids: Precomputed list of latest event IDs. Will be computed if None. Returns: - Dictionary of user IDs to their profileinfo. + Set of user IDs in the room. """ assert latest_event_ids is not None - logger.debug("calling resolve_state_groups from get_current_users_in_room") + logger.debug("calling resolve_state_groups from get_current_user_ids_in_room") entry = await self.resolve_state_groups_for_events(room_id, latest_event_ids) state = await entry.get_state(self._state_storage_controller, StateFilter.all()) - return await self.store.get_joined_users_from_state(room_id, state, entry) + return await self.store.get_joined_user_ids_from_state(room_id, state, entry) async def get_hosts_in_room_at_events( self, room_id: str, event_ids: Collection[str] diff --git a/synapse/state/v2.py b/synapse/state/v2.py index cf3045f82e..af03851c71 100644 --- a/synapse/state/v2.py +++ b/synapse/state/v2.py @@ -271,40 +271,41 @@ async def _get_power_level_for_sender( async def _get_auth_chain_difference( room_id: str, state_sets: Sequence[Mapping[Any, str]], - event_map: Dict[str, EventBase], + unpersisted_events: Dict[str, EventBase], state_res_store: StateResolutionStore, ) -> Set[str]: """Compare the auth chains of each state set and return the set of events - that only appear in some but not all of the auth chains. + that only appear in some, but not all of the auth chains. Args: - state_sets - event_map - state_res_store + state_sets: The input state sets we are trying to resolve across. + unpersisted_events: A map from event ID to EventBase containing all unpersisted + events involved in this resolution. + state_res_store: Returns: - Set of event IDs + The auth difference of the given state sets, as a set of event IDs. """ # The `StateResolutionStore.get_auth_chain_difference` function assumes that # all events passed to it (and their auth chains) have been persisted - # previously. This is not the case for any events in the `event_map`, and so - # we need to manually handle those events. + # previously. We need to manually handle any other events that are yet to be + # persisted. # - # We do this by: - # 1. calculating the auth chain difference for the state sets based on the - # events in `event_map` alone - # 2. replacing any events in the state_sets that are also in `event_map` - # with their auth events (recursively), and then calling - # `store.get_auth_chain_difference` as normal - # 3. adding the results of 1 and 2 together. - - # Map from event ID in `event_map` to their auth event IDs, and their auth - # event IDs if they appear in the `event_map`. This is the intersection of - # the event's auth chain with the events in the `event_map` *plus* their + # We do this in three steps: + # 1. Compute the set of unpersisted events belonging to the auth difference. + # 2. Replacing any unpersisted events in the state_sets with their auth events, + # recursively, until the state_sets contain only persisted events. + # Then we call `store.get_auth_chain_difference` as normal, which computes + # the set of persisted events belonging to the auth difference. + # 3. Adding the results of 1 and 2 together. + + # Map from event ID in `unpersisted_events` to their auth event IDs, and their auth + # event IDs if they appear in the `unpersisted_events`. This is the intersection of + # the event's auth chain with the events in `unpersisted_events` *plus* their # auth event IDs. events_to_auth_chain: Dict[str, Set[str]] = {} - for event in event_map.values(): + for event in unpersisted_events.values(): chain = {event.event_id} events_to_auth_chain[event.event_id] = chain @@ -312,16 +313,16 @@ async def _get_auth_chain_difference( while to_search: for auth_id in to_search.pop().auth_event_ids(): chain.add(auth_id) - auth_event = event_map.get(auth_id) + auth_event = unpersisted_events.get(auth_id) if auth_event: to_search.append(auth_event) - # We now a) calculate the auth chain difference for the unpersisted events - # and b) work out the state sets to pass to the store. + # We now 1) calculate the auth chain difference for the unpersisted events + # and 2) work out the state sets to pass to the store. # - # Note: If the `event_map` is empty (which is the common case), we can do a + # Note: If there are no `unpersisted_events` (which is the common case), we can do a # much simpler calculation. - if event_map: + if unpersisted_events: # The list of state sets to pass to the store, where each state set is a set # of the event ids making up the state. This is similar to `state_sets`, # except that (a) we only have event ids, not the complete @@ -344,14 +345,18 @@ async def _get_auth_chain_difference( for event_id in state_set.values(): event_chain = events_to_auth_chain.get(event_id) if event_chain is not None: - # We have an event in `event_map`. We add all the auth - # events that it references (that aren't also in `event_map`). - set_ids.update(e for e in event_chain if e not in event_map) + # We have an unpersisted event. We add all the auth + # events that it references which are also unpersisted. + set_ids.update( + e for e in event_chain if e not in unpersisted_events + ) # We also add the full chain of unpersisted event IDs # referenced by this state set, so that we can work out the # auth chain difference of the unpersisted events. - unpersisted_ids.update(e for e in event_chain if e in event_map) + unpersisted_ids.update( + e for e in event_chain if e in unpersisted_events + ) else: set_ids.add(event_id) @@ -361,15 +366,15 @@ async def _get_auth_chain_difference( union = unpersisted_set_ids[0].union(*unpersisted_set_ids[1:]) intersection = unpersisted_set_ids[0].intersection(*unpersisted_set_ids[1:]) - difference_from_event_map: Collection[str] = union - intersection + auth_difference_unpersisted_part: Collection[str] = union - intersection else: - difference_from_event_map = () + auth_difference_unpersisted_part = () state_sets_ids = [set(state_set.values()) for state_set in state_sets] difference = await state_res_store.get_auth_chain_difference( room_id, state_sets_ids ) - difference.update(difference_from_event_map) + difference.update(auth_difference_unpersisted_part) return difference diff --git a/synapse/storage/controllers/persist_events.py b/synapse/storage/controllers/persist_events.py index cf98b0ab48..dad3731b9b 100644 --- a/synapse/storage/controllers/persist_events.py +++ b/synapse/storage/controllers/persist_events.py @@ -45,8 +45,14 @@ from twisted.internet import defer from synapse.api.constants import EventTypes, Membership from synapse.events import EventBase from synapse.events.snapshot import EventContext -from synapse.logging import opentracing from synapse.logging.context import PreserveLoggingContext, make_deferred_yieldable +from synapse.logging.opentracing import ( + SynapseTags, + active_span, + set_tag, + start_active_span_follows_from, + trace, +) from synapse.metrics.background_process_metrics import run_as_background_process from synapse.storage.controllers.state import StateStorageController from synapse.storage.databases import Databases @@ -223,7 +229,7 @@ class _EventPeristenceQueue(Generic[_PersistResult]): queue.append(end_item) # also add our active opentracing span to the item so that we get a link back - span = opentracing.active_span() + span = active_span() if span: end_item.parent_opentracing_span_contexts.append(span.context) @@ -234,7 +240,7 @@ class _EventPeristenceQueue(Generic[_PersistResult]): res = await make_deferred_yieldable(end_item.deferred.observe()) # add another opentracing span which links to the persist trace. - with opentracing.start_active_span_follows_from( + with start_active_span_follows_from( f"{task.name}_complete", (end_item.opentracing_span_context,) ): pass @@ -266,7 +272,7 @@ class _EventPeristenceQueue(Generic[_PersistResult]): queue = self._get_drainining_queue(room_id) for item in queue: try: - with opentracing.start_active_span_follows_from( + with start_active_span_follows_from( item.task.name, item.parent_opentracing_span_contexts, inherit_force_tracing=True, @@ -355,7 +361,7 @@ class EventsPersistenceStorageController: f"Found an unexpected task type in event persistence queue: {task}" ) - @opentracing.trace + @trace async def persist_events( self, events_and_contexts: Iterable[Tuple[EventBase, EventContext]], @@ -380,9 +386,21 @@ class EventsPersistenceStorageController: PartialStateConflictError: if attempting to persist a partial state event in a room that has been un-partial stated. """ + event_ids: List[str] = [] partitioned: Dict[str, List[Tuple[EventBase, EventContext]]] = {} for event, ctx in events_and_contexts: partitioned.setdefault(event.room_id, []).append((event, ctx)) + event_ids.append(event.event_id) + + set_tag( + SynapseTags.FUNC_ARG_PREFIX + "event_ids", + str(event_ids), + ) + set_tag( + SynapseTags.FUNC_ARG_PREFIX + "event_ids.length", + str(len(event_ids)), + ) + set_tag(SynapseTags.FUNC_ARG_PREFIX + "backfilled", str(backfilled)) async def enqueue( item: Tuple[str, List[Tuple[EventBase, EventContext]]] @@ -418,7 +436,7 @@ class EventsPersistenceStorageController: self.main_store.get_room_max_token(), ) - @opentracing.trace + @trace async def persist_event( self, event: EventBase, context: EventContext, backfilled: bool = False ) -> Tuple[EventBase, PersistedEventPosition, RoomStreamToken]: diff --git a/synapse/storage/controllers/state.py b/synapse/storage/controllers/state.py index 0d480f1014..f9ffd0e29e 100644 --- a/synapse/storage/controllers/state.py +++ b/synapse/storage/controllers/state.py @@ -29,7 +29,8 @@ from typing import ( from synapse.api.constants import EventTypes from synapse.events import EventBase -from synapse.logging.opentracing import trace +from synapse.logging.opentracing import tag_args, trace +from synapse.storage.roommember import ProfileInfo from synapse.storage.state import StateFilter from synapse.storage.util.partial_state_events_tracker import ( PartialCurrentStateTracker, @@ -228,10 +229,12 @@ class StateStorageController: return {event: event_to_state[event] for event in event_ids} @trace + @tag_args async def get_state_ids_for_events( self, event_ids: Collection[str], state_filter: Optional[StateFilter] = None, + await_full_state: bool = True, ) -> Dict[str, StateMap[str]]: """ Get the state dicts corresponding to a list of events, containing the event_ids @@ -240,6 +243,9 @@ class StateStorageController: Args: event_ids: events whose state should be returned state_filter: The state filter used to fetch state from the database. + await_full_state: if `True`, will block if we do not yet have complete state + at these events and `state_filter` is not satisfied by partial state. + Defaults to `True`. Returns: A dict from event_id -> (type, state_key) -> event_id @@ -248,8 +254,12 @@ class StateStorageController: RuntimeError if we don't have a state group for one or more of the events (ie they are outliers or unknown) """ - await_full_state = True - if state_filter and not state_filter.must_await_full_state(self._is_mine_id): + if ( + await_full_state + and state_filter + and not state_filter.must_await_full_state(self._is_mine_id) + ): + # Full state is not required if the state filter is restrictive enough. await_full_state = False event_to_groups = await self.get_state_group_for_events( @@ -292,7 +302,10 @@ class StateStorageController: @trace async def get_state_ids_for_event( - self, event_id: str, state_filter: Optional[StateFilter] = None + self, + event_id: str, + state_filter: Optional[StateFilter] = None, + await_full_state: bool = True, ) -> StateMap[str]: """ Get the state dict corresponding to a particular event @@ -300,6 +313,9 @@ class StateStorageController: Args: event_id: event whose state should be returned state_filter: The state filter used to fetch state from the database. + await_full_state: if `True`, will block if we do not yet have complete state + at the event and `state_filter` is not satisfied by partial state. + Defaults to `True`. Returns: A dict from (type, state_key) -> state_event_id @@ -309,7 +325,9 @@ class StateStorageController: outlier or is unknown) """ state_map = await self.get_state_ids_for_events( - [event_id], state_filter or StateFilter.all() + [event_id], + state_filter or StateFilter.all(), + await_full_state=await_full_state, ) return state_map[event_id] @@ -332,6 +350,7 @@ class StateStorageController: ) @trace + @tag_args async def get_state_group_for_events( self, event_ids: Collection[str], @@ -473,6 +492,7 @@ class StateStorageController: prev_stream_id, max_stream_id ) + @trace async def get_current_state( self, room_id: str, state_filter: Optional[StateFilter] = None ) -> StateMap[EventBase]: @@ -506,3 +526,15 @@ class StateStorageController: await self._partial_state_room_tracker.await_full_state(room_id) return await self.stores.main.get_current_hosts_in_room(room_id) + + async def get_users_in_room_with_profiles( + self, room_id: str + ) -> Dict[str, ProfileInfo]: + """ + Get the current users in the room with their profiles. + If the room is currently partial-stated, this will block until the room has + full state. + """ + await self._partial_state_room_tracker.await_full_state(room_id) + + return await self.stores.main.get_users_in_room_with_profiles(room_id) diff --git a/synapse/storage/databases/main/account_data.py b/synapse/storage/databases/main/account_data.py index 9af9f4f18e..c38b8a9e5a 100644 --- a/synapse/storage/databases/main/account_data.py +++ b/synapse/storage/databases/main/account_data.py @@ -650,9 +650,6 @@ class AccountDataWorkerStore(PushRulesWorkerStore, CacheInvalidationWorkerStore) txn, self.get_account_data_for_room, (user_id,) ) self._invalidate_cache_and_stream(txn, self.get_push_rules_for_user, (user_id,)) - self._invalidate_cache_and_stream( - txn, self.get_push_rules_enabled_for_user, (user_id,) - ) # This user might be contained in the ignored_by cache for other users, # so we have to invalidate it all. self._invalidate_all_cache_and_stream(txn, self.ignored_by) diff --git a/synapse/storage/databases/main/event_federation.py b/synapse/storage/databases/main/event_federation.py index eec55b6478..c836078da6 100644 --- a/synapse/storage/databases/main/event_federation.py +++ b/synapse/storage/databases/main/event_federation.py @@ -33,6 +33,7 @@ from synapse.api.constants import MAX_DEPTH, EventTypes from synapse.api.errors import StoreError from synapse.api.room_versions import EventFormatVersions, RoomVersion from synapse.events import EventBase, make_event_from_dict +from synapse.logging.opentracing import tag_args, trace from synapse.metrics.background_process_metrics import wrap_as_background_process from synapse.storage._base import SQLBaseStore, db_to_json, make_in_list_sql_clause from synapse.storage.database import ( @@ -126,6 +127,8 @@ class EventFederationWorkerStore(SignatureWorkerStore, EventsWorkerStore, SQLBas ) return await self.get_events_as_list(event_ids) + @trace + @tag_args async def get_auth_chain_ids( self, room_id: str, @@ -709,6 +712,8 @@ class EventFederationWorkerStore(SignatureWorkerStore, EventsWorkerStore, SQLBas # Return all events where not all sets can reach them. return {eid for eid, n in event_to_missing_sets.items() if n} + @trace + @tag_args async def get_oldest_event_ids_with_depth_in_room( self, room_id: str ) -> List[Tuple[str, int]]: @@ -767,6 +772,7 @@ class EventFederationWorkerStore(SignatureWorkerStore, EventsWorkerStore, SQLBas room_id, ) + @trace async def get_insertion_event_backward_extremities_in_room( self, room_id: str ) -> List[Tuple[str, int]]: @@ -1339,6 +1345,8 @@ class EventFederationWorkerStore(SignatureWorkerStore, EventsWorkerStore, SQLBas event_results.reverse() return event_results + @trace + @tag_args async def get_successor_events(self, event_id: str) -> List[str]: """Fetch all events that have the given event as a prev event @@ -1375,6 +1383,7 @@ class EventFederationWorkerStore(SignatureWorkerStore, EventsWorkerStore, SQLBas _delete_old_forward_extrem_cache_txn, ) + @trace async def insert_insertion_extremity(self, event_id: str, room_id: str) -> None: await self.db_pool.simple_upsert( table="insertion_event_extremities", diff --git a/synapse/storage/databases/main/event_push_actions.py b/synapse/storage/databases/main/event_push_actions.py index 161aad0f89..8dfa545c27 100644 --- a/synapse/storage/databases/main/event_push_actions.py +++ b/synapse/storage/databases/main/event_push_actions.py @@ -74,7 +74,17 @@ receipt. """ import logging -from typing import TYPE_CHECKING, Dict, List, Optional, Tuple, Union, cast +from typing import ( + TYPE_CHECKING, + Collection, + Dict, + List, + Mapping, + Optional, + Tuple, + Union, + cast, +) import attr @@ -154,7 +164,9 @@ class NotifCounts: highlight_count: int = 0 -def _serialize_action(actions: List[Union[dict, str]], is_highlight: bool) -> str: +def _serialize_action( + actions: Collection[Union[Mapping, str]], is_highlight: bool +) -> str: """Custom serializer for actions. This allows us to "compress" common actions. We use the fact that most users have the same actions for notifs (and for @@ -227,7 +239,7 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas user_id: str, ) -> NotifCounts: """Get the notification count, the highlight count and the unread message count - for a given user in a given room after the given read receipt. + for a given user in a given room after their latest read receipt. Note that this function assumes the user to be a current member of the room, since it's either called by the sync handler to handle joined room entries, or by @@ -238,9 +250,8 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas user_id: The user to retrieve the counts for. Returns - A dict containing the counts mentioned earlier in this docstring, - respectively under the keys "notify_count", "highlight_count" and - "unread_count". + A NotifCounts object containing the notification count, the highlight count + and the unread message count. """ return await self.db_pool.runInteraction( "get_unread_event_push_actions_by_room", @@ -255,6 +266,7 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas room_id: str, user_id: str, ) -> NotifCounts: + # Get the stream ordering of the user's latest receipt in the room. result = self.get_last_receipt_for_user_txn( txn, user_id, @@ -266,13 +278,11 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas ), ) - stream_ordering = None if result: _, stream_ordering = result - if stream_ordering is None: - # Either last_read_event_id is None, or it's an event we don't have (e.g. - # because it's been purged), in which case retrieve the stream ordering for + else: + # If the user has no receipts in the room, retrieve the stream ordering for # the latest membership event from this user in this room (which we assume is # a join). event_id = self.db_pool.simple_select_one_onecol_txn( @@ -289,10 +299,26 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas ) def _get_unread_counts_by_pos_txn( - self, txn: LoggingTransaction, room_id: str, user_id: str, stream_ordering: int + self, + txn: LoggingTransaction, + room_id: str, + user_id: str, + receipt_stream_ordering: int, ) -> NotifCounts: """Get the number of unread messages for a user/room that have happened since the given stream ordering. + + Args: + txn: The database transaction. + room_id: The room ID to get unread counts for. + user_id: The user ID to get unread counts for. + receipt_stream_ordering: The stream ordering of the user's latest + receipt in the room. If there are no receipts, the stream ordering + of the user's join event. + + Returns + A NotifCounts object containing the notification count, the highlight count + and the unread message count. """ counts = NotifCounts() @@ -320,7 +346,7 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas OR last_receipt_stream_ordering = ? ) """, - (room_id, user_id, stream_ordering, stream_ordering), + (room_id, user_id, receipt_stream_ordering, receipt_stream_ordering), ) row = txn.fetchone() @@ -338,17 +364,20 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas AND stream_ordering > ? AND highlight = 1 """ - txn.execute(sql, (user_id, room_id, stream_ordering)) + txn.execute(sql, (user_id, room_id, receipt_stream_ordering)) row = txn.fetchone() if row: counts.highlight_count += row[0] # Finally we need to count push actions that aren't included in the - # summary returned above, e.g. recent events that haven't been - # summarised yet, or the summary is empty due to a recent read receipt. - stream_ordering = max(stream_ordering, summary_stream_ordering) + # summary returned above. This might be due to recent events that haven't + # been summarised yet or the summary is out of date due to a recent read + # receipt. + start_unread_stream_ordering = max( + receipt_stream_ordering, summary_stream_ordering + ) notify_count, unread_count = self._get_notif_unread_count_for_user_room( - txn, room_id, user_id, stream_ordering + txn, room_id, user_id, start_unread_stream_ordering ) counts.notify_count += notify_count @@ -430,6 +459,32 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas return await self.db_pool.runInteraction("get_push_action_users_in_range", f) + def _get_receipts_by_room_txn( + self, txn: LoggingTransaction, user_id: str + ) -> List[Tuple[str, int]]: + receipt_types_clause, args = make_in_list_sql_clause( + self.database_engine, + "receipt_type", + ( + ReceiptTypes.READ, + ReceiptTypes.READ_PRIVATE, + ReceiptTypes.UNSTABLE_READ_PRIVATE, + ), + ) + + sql = f""" + SELECT room_id, MAX(stream_ordering) + FROM receipts_linearized + INNER JOIN events USING (room_id, event_id) + WHERE {receipt_types_clause} + AND user_id = ? + GROUP BY room_id + """ + + args.extend((user_id,)) + txn.execute(sql, args) + return cast(List[Tuple[str, int]], txn.fetchall()) + async def get_unread_push_actions_for_user_in_range_for_http( self, user_id: str, @@ -453,106 +508,45 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas The list will have between 0~limit entries. """ - # find rooms that have a read receipt in them and return the next - # push actions - def get_after_receipt( - txn: LoggingTransaction, - ) -> List[Tuple[str, str, int, str, bool]]: - # find rooms that have a read receipt in them and return the next - # push actions - - receipt_types_clause, args = make_in_list_sql_clause( - self.database_engine, - "receipt_type", - ( - ReceiptTypes.READ, - ReceiptTypes.READ_PRIVATE, - ReceiptTypes.UNSTABLE_READ_PRIVATE, - ), - ) - - sql = f""" - SELECT ep.event_id, ep.room_id, ep.stream_ordering, ep.actions, - ep.highlight - FROM ( - SELECT room_id, - MAX(stream_ordering) as stream_ordering - FROM events - INNER JOIN receipts_linearized USING (room_id, event_id) - WHERE {receipt_types_clause} AND user_id = ? - GROUP BY room_id - ) AS rl, - event_push_actions AS ep - WHERE - ep.room_id = rl.room_id - AND ep.stream_ordering > rl.stream_ordering - AND ep.user_id = ? - AND ep.stream_ordering > ? - AND ep.stream_ordering <= ? - AND ep.notif = 1 - ORDER BY ep.stream_ordering ASC LIMIT ? - """ - args.extend( - (user_id, user_id, min_stream_ordering, max_stream_ordering, limit) - ) - txn.execute(sql, args) - return cast(List[Tuple[str, str, int, str, bool]], txn.fetchall()) - - after_read_receipt = await self.db_pool.runInteraction( - "get_unread_push_actions_for_user_in_range_http_arr", get_after_receipt + receipts_by_room = dict( + await self.db_pool.runInteraction( + "get_unread_push_actions_for_user_in_range_http_receipts", + self._get_receipts_by_room_txn, + user_id=user_id, + ), ) - # There are rooms with push actions in them but you don't have a read receipt in - # them e.g. rooms you've been invited to, so get push actions for rooms which do - # not have read receipts in them too. - def get_no_receipt( + def get_push_actions_txn( txn: LoggingTransaction, ) -> List[Tuple[str, str, int, str, bool]]: - receipt_types_clause, args = make_in_list_sql_clause( - self.database_engine, - "receipt_type", - ( - ReceiptTypes.READ, - ReceiptTypes.READ_PRIVATE, - ReceiptTypes.UNSTABLE_READ_PRIVATE, - ), - ) - - sql = f""" - SELECT ep.event_id, ep.room_id, ep.stream_ordering, ep.actions, - ep.highlight + sql = """ + SELECT ep.event_id, ep.room_id, ep.stream_ordering, ep.actions, ep.highlight FROM event_push_actions AS ep - INNER JOIN events AS e USING (room_id, event_id) WHERE - ep.room_id NOT IN ( - SELECT room_id FROM receipts_linearized - WHERE {receipt_types_clause} AND user_id = ? - GROUP BY room_id - ) - AND ep.user_id = ? + ep.user_id = ? AND ep.stream_ordering > ? AND ep.stream_ordering <= ? AND ep.notif = 1 ORDER BY ep.stream_ordering ASC LIMIT ? """ - args.extend( - (user_id, user_id, min_stream_ordering, max_stream_ordering, limit) - ) - txn.execute(sql, args) + txn.execute(sql, (user_id, min_stream_ordering, max_stream_ordering, limit)) return cast(List[Tuple[str, str, int, str, bool]], txn.fetchall()) - no_read_receipt = await self.db_pool.runInteraction( - "get_unread_push_actions_for_user_in_range_http_nrr", get_no_receipt + push_actions = await self.db_pool.runInteraction( + "get_unread_push_actions_for_user_in_range_http", get_push_actions_txn ) notifs = [ HttpPushAction( - event_id=row[0], - room_id=row[1], - stream_ordering=row[2], - actions=_deserialize_action(row[3], row[4]), + event_id=event_id, + room_id=room_id, + stream_ordering=stream_ordering, + actions=_deserialize_action(actions, highlight), ) - for row in after_read_receipt + no_read_receipt + for event_id, room_id, stream_ordering, actions, highlight in push_actions + # Only include push actions with a stream ordering after any receipt, or without any + # receipt present (invited to but never read rooms). + if stream_ordering > receipts_by_room.get(room_id, 0) ] # Now sort it so it's ordered correctly, since currently it will @@ -588,106 +582,49 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas The list will have between 0~limit entries. """ - # find rooms that have a read receipt in them and return the most recent - # push actions - def get_after_receipt( - txn: LoggingTransaction, - ) -> List[Tuple[str, str, int, str, bool, int]]: - receipt_types_clause, args = make_in_list_sql_clause( - self.database_engine, - "receipt_type", - ( - ReceiptTypes.READ, - ReceiptTypes.READ_PRIVATE, - ReceiptTypes.UNSTABLE_READ_PRIVATE, - ), - ) - - sql = f""" - SELECT ep.event_id, ep.room_id, ep.stream_ordering, ep.actions, - ep.highlight, e.received_ts - FROM ( - SELECT room_id, - MAX(stream_ordering) as stream_ordering - FROM events - INNER JOIN receipts_linearized USING (room_id, event_id) - WHERE {receipt_types_clause} AND user_id = ? - GROUP BY room_id - ) AS rl, - event_push_actions AS ep - INNER JOIN events AS e USING (room_id, event_id) - WHERE - ep.room_id = rl.room_id - AND ep.stream_ordering > rl.stream_ordering - AND ep.user_id = ? - AND ep.stream_ordering > ? - AND ep.stream_ordering <= ? - AND ep.notif = 1 - ORDER BY ep.stream_ordering DESC LIMIT ? - """ - args.extend( - (user_id, user_id, min_stream_ordering, max_stream_ordering, limit) - ) - txn.execute(sql, args) - return cast(List[Tuple[str, str, int, str, bool, int]], txn.fetchall()) - - after_read_receipt = await self.db_pool.runInteraction( - "get_unread_push_actions_for_user_in_range_email_arr", get_after_receipt + receipts_by_room = dict( + await self.db_pool.runInteraction( + "get_unread_push_actions_for_user_in_range_email_receipts", + self._get_receipts_by_room_txn, + user_id=user_id, + ), ) - # There are rooms with push actions in them but you don't have a read receipt in - # them e.g. rooms you've been invited to, so get push actions for rooms which do - # not have read receipts in them too. - def get_no_receipt( + def get_push_actions_txn( txn: LoggingTransaction, ) -> List[Tuple[str, str, int, str, bool, int]]: - receipt_types_clause, args = make_in_list_sql_clause( - self.database_engine, - "receipt_type", - ( - ReceiptTypes.READ, - ReceiptTypes.READ_PRIVATE, - ReceiptTypes.UNSTABLE_READ_PRIVATE, - ), - ) - - sql = f""" + sql = """ SELECT ep.event_id, ep.room_id, ep.stream_ordering, ep.actions, ep.highlight, e.received_ts FROM event_push_actions AS ep INNER JOIN events AS e USING (room_id, event_id) WHERE - ep.room_id NOT IN ( - SELECT room_id FROM receipts_linearized - WHERE {receipt_types_clause} AND user_id = ? - GROUP BY room_id - ) - AND ep.user_id = ? + ep.user_id = ? AND ep.stream_ordering > ? AND ep.stream_ordering <= ? AND ep.notif = 1 ORDER BY ep.stream_ordering DESC LIMIT ? """ - args.extend( - (user_id, user_id, min_stream_ordering, max_stream_ordering, limit) - ) - txn.execute(sql, args) + txn.execute(sql, (user_id, min_stream_ordering, max_stream_ordering, limit)) return cast(List[Tuple[str, str, int, str, bool, int]], txn.fetchall()) - no_read_receipt = await self.db_pool.runInteraction( - "get_unread_push_actions_for_user_in_range_email_nrr", get_no_receipt + push_actions = await self.db_pool.runInteraction( + "get_unread_push_actions_for_user_in_range_email", get_push_actions_txn ) # Make a list of dicts from the two sets of results. notifs = [ EmailPushAction( - event_id=row[0], - room_id=row[1], - stream_ordering=row[2], - actions=_deserialize_action(row[3], row[4]), - received_ts=row[5], + event_id=event_id, + room_id=room_id, + stream_ordering=stream_ordering, + actions=_deserialize_action(actions, highlight), + received_ts=received_ts, ) - for row in after_read_receipt + no_read_receipt + for event_id, room_id, stream_ordering, actions, highlight, received_ts in push_actions + # Only include push actions with a stream ordering after any receipt, or without any + # receipt present (invited to but never read rooms). + if stream_ordering > receipts_by_room.get(room_id, 0) ] # Now sort it so it's ordered correctly, since currently it will @@ -733,7 +670,7 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas async def add_push_actions_to_staging( self, event_id: str, - user_id_actions: Dict[str, List[Union[dict, str]]], + user_id_actions: Dict[str, Collection[Union[Mapping, str]]], count_as_unread: bool, ) -> None: """Add the push actions for the event to the push action staging area. @@ -750,7 +687,7 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas # This is a helper function for generating the necessary tuple that # can be used to insert into the `event_push_actions_staging` table. def _gen_entry( - user_id: str, actions: List[Union[dict, str]] + user_id: str, actions: Collection[Union[Mapping, str]] ) -> Tuple[str, str, str, int, int, int]: is_highlight = 1 if _action_has_highlight(actions) else 0 notif = 1 if "notify" in actions else 0 @@ -1151,8 +1088,6 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas txn: The database transaction. old_rotate_stream_ordering: The previous maximum event stream ordering. rotate_to_stream_ordering: The new maximum event stream ordering to summarise. - - Returns whether the archiving process has caught up or not. """ # Calculate the new counts that should be upserted into event_push_summary @@ -1238,9 +1173,7 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas (rotate_to_stream_ordering,), ) - async def _remove_old_push_actions_that_have_rotated( - self, - ) -> None: + async def _remove_old_push_actions_that_have_rotated(self) -> None: """Clear out old push actions that have been summarised.""" # We want to clear out anything that is older than a day that *has* already @@ -1397,7 +1330,7 @@ class EventPushActionsStore(EventPushActionsWorkerStore): ] -def _action_has_highlight(actions: List[Union[dict, str]]) -> bool: +def _action_has_highlight(actions: Collection[Union[Mapping, str]]) -> bool: for action in actions: if not isinstance(action, dict): continue diff --git a/synapse/storage/databases/main/events.py b/synapse/storage/databases/main/events.py index 5560b38a48..a4010ee28d 100644 --- a/synapse/storage/databases/main/events.py +++ b/synapse/storage/databases/main/events.py @@ -40,6 +40,7 @@ from synapse.api.errors import Codes, SynapseError from synapse.api.room_versions import RoomVersions from synapse.events import EventBase, relation_from_event from synapse.events.snapshot import EventContext +from synapse.logging.opentracing import trace from synapse.storage._base import db_to_json, make_in_list_sql_clause from synapse.storage.database import ( DatabasePool, @@ -145,6 +146,7 @@ class PersistEventsStore: self._backfill_id_gen: AbstractStreamIdGenerator = self.store._backfill_id_gen self._stream_id_gen: AbstractStreamIdGenerator = self.store._stream_id_gen + @trace async def _persist_events_and_state_updates( self, events_and_contexts: List[Tuple[EventBase, EventContext]], diff --git a/synapse/storage/databases/main/events_worker.py b/synapse/storage/databases/main/events_worker.py index b07d812ae2..8a7cdb024d 100644 --- a/synapse/storage/databases/main/events_worker.py +++ b/synapse/storage/databases/main/events_worker.py @@ -54,6 +54,7 @@ from synapse.logging.context import ( current_context, make_deferred_yieldable, ) +from synapse.logging.opentracing import start_active_span, tag_args, trace from synapse.metrics.background_process_metrics import ( run_as_background_process, wrap_as_background_process, @@ -430,6 +431,8 @@ class EventsWorkerStore(SQLBaseStore): return {e.event_id: e for e in events} + @trace + @tag_args async def get_events_as_list( self, event_ids: Collection[str], @@ -1090,23 +1093,42 @@ class EventsWorkerStore(SQLBaseStore): """ fetched_event_ids: Set[str] = set() fetched_events: Dict[str, _EventRow] = {} - events_to_fetch = event_ids - while events_to_fetch: - row_map = await self._enqueue_events(events_to_fetch) + async def _fetch_event_ids_and_get_outstanding_redactions( + event_ids_to_fetch: Collection[str], + ) -> Collection[str]: + """ + Fetch all of the given event_ids and return any associated redaction event_ids + that we still need to fetch in the next iteration. + """ + row_map = await self._enqueue_events(event_ids_to_fetch) # we need to recursively fetch any redactions of those events redaction_ids: Set[str] = set() - for event_id in events_to_fetch: + for event_id in event_ids_to_fetch: row = row_map.get(event_id) fetched_event_ids.add(event_id) if row: fetched_events[event_id] = row redaction_ids.update(row.redactions) - events_to_fetch = redaction_ids.difference(fetched_event_ids) - if events_to_fetch: - logger.debug("Also fetching redaction events %s", events_to_fetch) + event_ids_to_fetch = redaction_ids.difference(fetched_event_ids) + return event_ids_to_fetch + + # Grab the initial list of events requested + event_ids_to_fetch = await _fetch_event_ids_and_get_outstanding_redactions( + event_ids + ) + # Then go and recursively find all of the associated redactions + with start_active_span("recursively fetching redactions"): + while event_ids_to_fetch: + logger.debug("Also fetching redaction events %s", event_ids_to_fetch) + + event_ids_to_fetch = ( + await _fetch_event_ids_and_get_outstanding_redactions( + event_ids_to_fetch + ) + ) # build a map from event_id to EventBase event_map: Dict[str, EventBase] = {} @@ -1424,6 +1446,8 @@ class EventsWorkerStore(SQLBaseStore): return {r["event_id"] for r in rows} + @trace + @tag_args async def have_seen_events( self, room_id: str, event_ids: Iterable[str] ) -> Set[str]: diff --git a/synapse/storage/databases/main/push_rule.py b/synapse/storage/databases/main/push_rule.py index 768f95d16c..5079edd1e0 100644 --- a/synapse/storage/databases/main/push_rule.py +++ b/synapse/storage/databases/main/push_rule.py @@ -14,11 +14,23 @@ # limitations under the License. import abc import logging -from typing import TYPE_CHECKING, Collection, Dict, List, Optional, Tuple, Union, cast +from typing import ( + TYPE_CHECKING, + Any, + Collection, + Dict, + List, + Mapping, + Optional, + Sequence, + Tuple, + Union, + cast, +) from synapse.api.errors import StoreError from synapse.config.homeserver import ExperimentalConfig -from synapse.push.baserules import list_with_base_rules +from synapse.push.baserules import FilteredPushRules, PushRule, compile_push_rules from synapse.replication.slave.storage._slaved_id_tracker import SlavedIdTracker from synapse.storage._base import SQLBaseStore, db_to_json from synapse.storage.database import ( @@ -50,60 +62,30 @@ if TYPE_CHECKING: logger = logging.getLogger(__name__) -def _is_experimental_rule_enabled( - rule_id: str, experimental_config: ExperimentalConfig -) -> bool: - """Used by `_load_rules` to filter out experimental rules when they - have not been enabled. - """ - if ( - rule_id == "global/override/.org.matrix.msc3786.rule.room.server_acl" - and not experimental_config.msc3786_enabled - ): - return False - if ( - rule_id == "global/underride/.org.matrix.msc3772.thread_reply" - and not experimental_config.msc3772_enabled - ): - return False - return True - - def _load_rules( rawrules: List[JsonDict], enabled_map: Dict[str, bool], experimental_config: ExperimentalConfig, -) -> List[JsonDict]: - ruleslist = [] - for rawrule in rawrules: - rule = dict(rawrule) - rule["conditions"] = db_to_json(rawrule["conditions"]) - rule["actions"] = db_to_json(rawrule["actions"]) - rule["default"] = False - ruleslist.append(rule) - - # We're going to be mutating this a lot, so copy it. We also filter out - # any experimental default push rules that aren't enabled. - rules = [ - rule - for rule in list_with_base_rules(ruleslist) - if _is_experimental_rule_enabled(rule["rule_id"], experimental_config) - ] +) -> FilteredPushRules: + """Take the DB rows returned from the DB and convert them into a full + `FilteredPushRules` object. + """ - for i, rule in enumerate(rules): - rule_id = rule["rule_id"] + ruleslist = [ + PushRule( + rule_id=rawrule["rule_id"], + priority_class=rawrule["priority_class"], + conditions=db_to_json(rawrule["conditions"]), + actions=db_to_json(rawrule["actions"]), + ) + for rawrule in rawrules + ] - if rule_id not in enabled_map: - continue - if rule.get("enabled", True) == bool(enabled_map[rule_id]): - continue + push_rules = compile_push_rules(ruleslist) - # Rules are cached across users. - rule = dict(rule) - rule["enabled"] = bool(enabled_map[rule_id]) - rules[i] = rule + filtered_rules = FilteredPushRules(push_rules, enabled_map, experimental_config) - return rules + return filtered_rules # The ABCMeta metaclass ensures that it cannot be instantiated without @@ -162,7 +144,7 @@ class PushRulesWorkerStore( raise NotImplementedError() @cached(max_entries=5000) - async def get_push_rules_for_user(self, user_id: str) -> List[JsonDict]: + async def get_push_rules_for_user(self, user_id: str) -> FilteredPushRules: rows = await self.db_pool.simple_select_list( table="push_rules", keyvalues={"user_name": user_id}, @@ -183,7 +165,6 @@ class PushRulesWorkerStore( return _load_rules(rows, enabled_map, self.hs.config.experimental) - @cached(max_entries=5000) async def get_push_rules_enabled_for_user(self, user_id: str) -> Dict[str, bool]: results = await self.db_pool.simple_select_list( table="push_rules_enable", @@ -216,11 +197,11 @@ class PushRulesWorkerStore( @cachedList(cached_method_name="get_push_rules_for_user", list_name="user_ids") async def bulk_get_push_rules( self, user_ids: Collection[str] - ) -> Dict[str, List[JsonDict]]: + ) -> Dict[str, FilteredPushRules]: if not user_ids: return {} - results: Dict[str, List[JsonDict]] = {user_id: [] for user_id in user_ids} + raw_rules: Dict[str, List[JsonDict]] = {user_id: [] for user_id in user_ids} rows = await self.db_pool.simple_select_many_batch( table="push_rules", @@ -234,20 +215,19 @@ class PushRulesWorkerStore( rows.sort(key=lambda row: (-int(row["priority_class"]), -int(row["priority"]))) for row in rows: - results.setdefault(row["user_name"], []).append(row) + raw_rules.setdefault(row["user_name"], []).append(row) enabled_map_by_user = await self.bulk_get_push_rules_enabled(user_ids) - for user_id, rules in results.items(): + results: Dict[str, FilteredPushRules] = {} + + for user_id, rules in raw_rules.items(): results[user_id] = _load_rules( rules, enabled_map_by_user.get(user_id, {}), self.hs.config.experimental ) return results - @cachedList( - cached_method_name="get_push_rules_enabled_for_user", list_name="user_ids" - ) async def bulk_get_push_rules_enabled( self, user_ids: Collection[str] ) -> Dict[str, Dict[str, bool]]: @@ -262,6 +242,7 @@ class PushRulesWorkerStore( iterable=user_ids, retcols=("user_name", "rule_id", "enabled"), desc="bulk_get_push_rules_enabled", + batch_size=1000, ) for row in rows: enabled = bool(row["enabled"]) @@ -345,8 +326,8 @@ class PushRuleStore(PushRulesWorkerStore): user_id: str, rule_id: str, priority_class: int, - conditions: List[Dict[str, str]], - actions: List[Union[JsonDict, str]], + conditions: Sequence[Mapping[str, str]], + actions: Sequence[Union[Mapping[str, Any], str]], before: Optional[str] = None, after: Optional[str] = None, ) -> None: @@ -808,7 +789,6 @@ class PushRuleStore(PushRulesWorkerStore): self.db_pool.simple_insert_txn(txn, "push_rules_stream", values=values) txn.call_after(self.get_push_rules_for_user.invalidate, (user_id,)) - txn.call_after(self.get_push_rules_enabled_for_user.invalidate, (user_id,)) txn.call_after( self.push_rules_stream_cache.entity_has_changed, user_id, stream_id ) @@ -817,7 +797,7 @@ class PushRuleStore(PushRulesWorkerStore): return self._push_rules_stream_id_gen.get_current_token() async def copy_push_rule_from_room_to_room( - self, new_room_id: str, user_id: str, rule: dict + self, new_room_id: str, user_id: str, rule: PushRule ) -> None: """Copy a single push rule from one room to another for a specific user. @@ -827,21 +807,27 @@ class PushRuleStore(PushRulesWorkerStore): rule: A push rule. """ # Create new rule id - rule_id_scope = "/".join(rule["rule_id"].split("/")[:-1]) + rule_id_scope = "/".join(rule.rule_id.split("/")[:-1]) new_rule_id = rule_id_scope + "/" + new_room_id + new_conditions = [] + # Change room id in each condition - for condition in rule.get("conditions", []): + for condition in rule.conditions: + new_condition = condition if condition.get("key") == "room_id": - condition["pattern"] = new_room_id + new_condition = dict(condition) + new_condition["pattern"] = new_room_id + + new_conditions.append(new_condition) # Add the rule for the new room await self.add_push_rule( user_id=user_id, rule_id=new_rule_id, - priority_class=rule["priority_class"], - conditions=rule["conditions"], - actions=rule["actions"], + priority_class=rule.priority_class, + conditions=new_conditions, + actions=rule.actions, ) async def copy_push_rules_from_room_to_room_for_user( @@ -859,8 +845,11 @@ class PushRuleStore(PushRulesWorkerStore): user_push_rules = await self.get_push_rules_for_user(user_id) # Get rules relating to the old room and copy them to the new room - for rule in user_push_rules: - conditions = rule.get("conditions", []) + for rule, enabled in user_push_rules: + if not enabled: + continue + + conditions = rule.conditions if any( (c.get("key") == "room_id" and c.get("pattern") == old_room_id) for c in conditions diff --git a/synapse/storage/databases/main/receipts.py b/synapse/storage/databases/main/receipts.py index 0090c9f225..124c70ad37 100644 --- a/synapse/storage/databases/main/receipts.py +++ b/synapse/storage/databases/main/receipts.py @@ -161,7 +161,7 @@ class ReceiptsWorkerStore(SQLBaseStore): receipt_type: The receipt types to fetch. Returns: - The latest receipt, if one exists. + The event ID and stream ordering of the latest receipt, if one exists. """ clause, args = make_in_list_sql_clause( diff --git a/synapse/storage/databases/main/registration.py b/synapse/storage/databases/main/registration.py index cb63cd9b7d..7fb9c801da 100644 --- a/synapse/storage/databases/main/registration.py +++ b/synapse/storage/databases/main/registration.py @@ -69,9 +69,9 @@ class TokenLookupResult: """ user_id: str + token_id: int is_guest: bool = False shadow_banned: bool = False - token_id: Optional[int] = None device_id: Optional[str] = None valid_until_ms: Optional[int] = None token_owner: str = attr.ib() diff --git a/synapse/storage/databases/main/room.py b/synapse/storage/databases/main/room.py index 0f1f0d11ea..b7d4baa6bb 100644 --- a/synapse/storage/databases/main/room.py +++ b/synapse/storage/databases/main/room.py @@ -2001,9 +2001,15 @@ class RoomStore(RoomBackgroundUpdateStore, RoomWorkerStore): where_clause = "WHERE " + " AND ".join(filters) if len(filters) > 0 else "" + # We join on room_stats_state despite not using any columns from it + # because the join can influence the number of rows returned; + # e.g. a room that doesn't have state, maybe because it was deleted. + # The query returning the total count should be consistent with + # the query returning the results. sql = """ SELECT COUNT(*) as total_event_reports FROM event_reports AS er + JOIN room_stats_state ON room_stats_state.room_id = er.room_id {} """.format( where_clause diff --git a/synapse/storage/databases/main/roommember.py b/synapse/storage/databases/main/roommember.py index 93ff4816c8..9e5034b401 100644 --- a/synapse/storage/databases/main/roommember.py +++ b/synapse/storage/databases/main/roommember.py @@ -283,6 +283,9 @@ class RoomMemberWorkerStore(EventsWorkerStore): Returns: A mapping from user ID to ProfileInfo. + + Preconditions: + - There is full state available for the room (it is not partial-stated). """ def _get_users_in_room_with_profiles( @@ -531,6 +534,32 @@ class RoomMemberWorkerStore(EventsWorkerStore): desc="get_local_users_in_room", ) + async def check_local_user_in_room(self, user_id: str, room_id: str) -> bool: + """ + Check whether a given local user is currently joined to the given room. + + Returns: + A boolean indicating whether the user is currently joined to the room + + Raises: + Exeption when called with a non-local user to this homeserver + """ + if not self.hs.is_mine_id(user_id): + raise Exception( + "Cannot call 'check_local_user_in_room' on " + "non-local user %s" % (user_id,), + ) + + ( + membership, + member_event_id, + ) = await self.get_local_current_membership_for_user_in_room( + user_id=user_id, + room_id=room_id, + ) + + return membership == Membership.JOIN + async def get_local_current_membership_for_user_in_room( self, user_id: str, room_id: str ) -> Tuple[Optional[str], Optional[str]]: @@ -832,9 +861,9 @@ class RoomMemberWorkerStore(EventsWorkerStore): return shared_room_ids or frozenset() - async def get_joined_users_from_state( + async def get_joined_user_ids_from_state( self, room_id: str, state: StateMap[str], state_entry: "_StateCacheEntry" - ) -> Dict[str, ProfileInfo]: + ) -> Set[str]: state_group: Union[object, int] = state_entry.state_group if not state_group: # If state_group is None it means it has yet to be assigned a @@ -845,25 +874,25 @@ class RoomMemberWorkerStore(EventsWorkerStore): assert state_group is not None with Measure(self._clock, "get_joined_users_from_state"): - return await self._get_joined_users_from_context( + return await self._get_joined_user_ids_from_context( room_id, state_group, state, context=state_entry ) @cached(num_args=2, iterable=True, max_entries=100000) - async def _get_joined_users_from_context( + async def _get_joined_user_ids_from_context( self, room_id: str, state_group: Union[object, int], current_state_ids: StateMap[str], event: Optional[EventBase] = None, context: Optional["_StateCacheEntry"] = None, - ) -> Dict[str, ProfileInfo]: + ) -> Set[str]: # We don't use `state_group`, it's there so that we can cache based # on it. However, it's important that it's never None, since two current_states # with a state_group of None are likely to be different. assert state_group is not None - users_in_room = {} + users_in_room = set() member_event_ids = [ e_id for key, e_id in current_state_ids.items() @@ -876,11 +905,11 @@ class RoomMemberWorkerStore(EventsWorkerStore): # If we do then we can reuse that result and simply update it with # any membership changes in `delta_ids` if context.prev_group and context.delta_ids: - prev_res = self._get_joined_users_from_context.cache.get_immediate( + prev_res = self._get_joined_user_ids_from_context.cache.get_immediate( (room_id, context.prev_group), None ) - if prev_res and isinstance(prev_res, dict): - users_in_room = dict(prev_res) + if prev_res and isinstance(prev_res, set): + users_in_room = prev_res member_event_ids = [ e_id for key, e_id in context.delta_ids.items() @@ -888,7 +917,7 @@ class RoomMemberWorkerStore(EventsWorkerStore): ] for etype, state_key in context.delta_ids: if etype == EventTypes.Member: - users_in_room.pop(state_key, None) + users_in_room.discard(state_key) # We check if we have any of the member event ids in the event cache # before we ask the DB @@ -905,71 +934,64 @@ class RoomMemberWorkerStore(EventsWorkerStore): ev_entry = event_map.get(event_id) if ev_entry and not ev_entry.event.rejected_reason: if ev_entry.event.membership == Membership.JOIN: - users_in_room[ev_entry.event.state_key] = ProfileInfo( - display_name=ev_entry.event.content.get("displayname", None), - avatar_url=ev_entry.event.content.get("avatar_url", None), - ) + users_in_room.add(ev_entry.event.state_key) else: missing_member_event_ids.append(event_id) if missing_member_event_ids: - event_to_memberships = await self._get_joined_profiles_from_event_ids( + event_to_memberships = await self._get_user_ids_from_membership_event_ids( missing_member_event_ids ) - users_in_room.update(row for row in event_to_memberships.values() if row) + users_in_room.update( + user_id for user_id in event_to_memberships.values() if user_id + ) if event is not None and event.type == EventTypes.Member: if event.membership == Membership.JOIN: if event.event_id in member_event_ids: - users_in_room[event.state_key] = ProfileInfo( - display_name=event.content.get("displayname", None), - avatar_url=event.content.get("avatar_url", None), - ) + users_in_room.add(event.state_key) return users_in_room - @cached(max_entries=10000) - def _get_joined_profile_from_event_id( + @cached( + max_entries=10000, + # This name matches the old function that has been replaced - the cache name + # is kept here to maintain backwards compatibility. + name="_get_joined_profile_from_event_id", + ) + def _get_user_id_from_membership_event_id( self, event_id: str ) -> Optional[Tuple[str, ProfileInfo]]: raise NotImplementedError() @cachedList( - cached_method_name="_get_joined_profile_from_event_id", + cached_method_name="_get_user_id_from_membership_event_id", list_name="event_ids", ) - async def _get_joined_profiles_from_event_ids( + async def _get_user_ids_from_membership_event_ids( self, event_ids: Iterable[str] - ) -> Dict[str, Optional[Tuple[str, ProfileInfo]]]: + ) -> Dict[str, Optional[str]]: """For given set of member event_ids check if they point to a join - event and if so return the associated user and profile info. + event. Args: event_ids: The member event IDs to lookup Returns: - Map from event ID to `user_id` and ProfileInfo (or None if not join event). + Map from event ID to `user_id`, or None if event is not a join. """ rows = await self.db_pool.simple_select_many_batch( table="room_memberships", column="event_id", iterable=event_ids, - retcols=("user_id", "display_name", "avatar_url", "event_id"), + retcols=("user_id", "event_id"), keyvalues={"membership": Membership.JOIN}, batch_size=1000, - desc="_get_joined_profiles_from_event_ids", + desc="_get_user_ids_from_membership_event_ids", ) - return { - row["event_id"]: ( - row["user_id"], - ProfileInfo( - avatar_url=row["avatar_url"], display_name=row["display_name"] - ), - ) - for row in rows - } + return {row["event_id"]: row["user_id"] for row in rows} @cached(max_entries=10000) async def is_host_joined(self, room_id: str, host: str) -> bool: @@ -1128,12 +1150,12 @@ class RoomMemberWorkerStore(EventsWorkerStore): else: # The cache doesn't match the state group or prev state group, # so we calculate the result from first principles. - joined_users = await self.get_joined_users_from_state( + joined_user_ids = await self.get_joined_user_ids_from_state( room_id, state, state_entry ) cache.hosts_to_joined_users = {} - for user_id in joined_users: + for user_id in joined_user_ids: host = intern_string(get_domain_from_id(user_id)) cache.hosts_to_joined_users.setdefault(host, set()).add(user_id) @@ -1212,6 +1234,30 @@ class RoomMemberWorkerStore(EventsWorkerStore): "get_forgotten_rooms_for_user", _get_forgotten_rooms_for_user_txn ) + async def is_locally_forgotten_room(self, room_id: str) -> bool: + """Returns whether all local users have forgotten this room_id. + + Args: + room_id: The room ID to query. + + Returns: + Whether the room is forgotten. + """ + + sql = """ + SELECT count(*) > 0 FROM local_current_membership + INNER JOIN room_memberships USING (room_id, event_id) + WHERE + room_id = ? + AND forgotten = 0; + """ + + rows = await self.db_pool.execute("is_forgotten_room", None, sql, room_id) + + # `count(*)` returns always an integer + # If any rows still exist it means someone has not forgotten this room yet + return not rows[0][0] + async def get_rooms_user_has_been_in(self, user_id: str) -> Set[str]: """Get all rooms that the user has ever been in. diff --git a/synapse/storage/util/id_generators.py b/synapse/storage/util/id_generators.py index 3c13859faa..2dfe4c0b66 100644 --- a/synapse/storage/util/id_generators.py +++ b/synapse/storage/util/id_generators.py @@ -460,8 +460,17 @@ class MultiWriterIdGenerator(AbstractStreamIdGenerator): # Cast safety: this corresponds to the types returned by the query above. rows.extend(cast(Iterable[Tuple[str, int]], cur)) - # Sort so that we handle rows in order for each instance. - rows.sort() + # Sort by stream_id (ascending, lowest -> highest) so that we handle + # rows in order for each instance because we don't want to overwrite + # the current_position of an instance to a lower stream ID than + # we're actually at. + def sort_by_stream_id_key_func(row: Tuple[str, int]) -> int: + (instance, stream_id) = row + # If `stream_id` is ever `None`, we will see a `TypeError: '<' + # not supported between instances of 'NoneType' and 'X'` error. + return stream_id + + rows.sort(key=sort_by_stream_id_key_func) with self._lock: for ( diff --git a/synapse/storage/util/partial_state_events_tracker.py b/synapse/storage/util/partial_state_events_tracker.py index 466e5137f2..b4bf49dace 100644 --- a/synapse/storage/util/partial_state_events_tracker.py +++ b/synapse/storage/util/partial_state_events_tracker.py @@ -20,6 +20,7 @@ from twisted.internet import defer from twisted.internet.defer import Deferred from synapse.logging.context import PreserveLoggingContext, make_deferred_yieldable +from synapse.logging.opentracing import trace_with_opname from synapse.storage.databases.main.events_worker import EventsWorkerStore from synapse.storage.databases.main.room import RoomWorkerStore from synapse.util import unwrapFirstError @@ -58,6 +59,7 @@ class PartialStateEventsTracker: for o in observers: o.callback(None) + @trace_with_opname("PartialStateEventsTracker.await_full_state") async def await_full_state(self, event_ids: Collection[str]) -> None: """Wait for all the given events to have full state. @@ -151,6 +153,7 @@ class PartialCurrentStateTracker: for o in observers: o.callback(None) + @trace_with_opname("PartialCurrentStateTracker.await_full_state") async def await_full_state(self, room_id: str) -> None: # We add the deferred immediately so that the DB call to check for # partial state doesn't race when we unpartial the room. diff --git a/synapse/util/caches/__init__.py b/synapse/util/caches/__init__.py index 42f6abb5e1..bdf9b0dc8c 100644 --- a/synapse/util/caches/__init__.py +++ b/synapse/util/caches/__init__.py @@ -34,10 +34,10 @@ TRACK_MEMORY_USAGE = False caches_by_name: Dict[str, Sized] = {} collectors_by_name: Dict[str, "CacheMetric"] = {} -cache_size = Gauge("synapse_util_caches_cache:size", "", ["name"]) -cache_hits = Gauge("synapse_util_caches_cache:hits", "", ["name"]) -cache_evicted = Gauge("synapse_util_caches_cache:evicted_size", "", ["name", "reason"]) -cache_total = Gauge("synapse_util_caches_cache:total", "", ["name"]) +cache_size = Gauge("synapse_util_caches_cache_size", "", ["name"]) +cache_hits = Gauge("synapse_util_caches_cache_hits", "", ["name"]) +cache_evicted = Gauge("synapse_util_caches_cache_evicted_size", "", ["name", "reason"]) +cache_total = Gauge("synapse_util_caches_cache_total", "", ["name"]) cache_max_size = Gauge("synapse_util_caches_cache_max_size", "", ["name"]) cache_memory_usage = Gauge( "synapse_util_caches_cache_size_bytes", @@ -45,12 +45,12 @@ cache_memory_usage = Gauge( ["name"], ) -response_cache_size = Gauge("synapse_util_caches_response_cache:size", "", ["name"]) -response_cache_hits = Gauge("synapse_util_caches_response_cache:hits", "", ["name"]) +response_cache_size = Gauge("synapse_util_caches_response_cache_size", "", ["name"]) +response_cache_hits = Gauge("synapse_util_caches_response_cache_hits", "", ["name"]) response_cache_evicted = Gauge( - "synapse_util_caches_response_cache:evicted_size", "", ["name", "reason"] + "synapse_util_caches_response_cache_evicted_size", "", ["name", "reason"] ) -response_cache_total = Gauge("synapse_util_caches_response_cache:total", "", ["name"]) +response_cache_total = Gauge("synapse_util_caches_response_cache_total", "", ["name"]) class EvictionReason(Enum): diff --git a/synapse/util/caches/deferred_cache.py b/synapse/util/caches/deferred_cache.py index 1d6ec22191..6425f851ea 100644 --- a/synapse/util/caches/deferred_cache.py +++ b/synapse/util/caches/deferred_cache.py @@ -14,15 +14,19 @@ # See the License for the specific language governing permissions and # limitations under the License. +import abc import enum import threading from typing import ( Callable, + Collection, + Dict, Generic, - Iterable, MutableMapping, Optional, + Set, Sized, + Tuple, TypeVar, Union, cast, @@ -31,7 +35,6 @@ from typing import ( from prometheus_client import Gauge from twisted.internet import defer -from twisted.python import failure from twisted.python.failure import Failure from synapse.util.async_helpers import ObservableDeferred @@ -94,7 +97,7 @@ class DeferredCache(Generic[KT, VT]): # _pending_deferred_cache maps from the key value to a `CacheEntry` object. self._pending_deferred_cache: Union[ - TreeCache, "MutableMapping[KT, CacheEntry]" + TreeCache, "MutableMapping[KT, CacheEntry[KT, VT]]" ] = cache_type() def metrics_cb() -> None: @@ -159,15 +162,16 @@ class DeferredCache(Generic[KT, VT]): Raises: KeyError if the key is not found in the cache """ - callbacks = [callback] if callback else [] val = self._pending_deferred_cache.get(key, _Sentinel.sentinel) if val is not _Sentinel.sentinel: - val.callbacks.update(callbacks) + val.add_invalidation_callback(key, callback) if update_metrics: m = self.cache.metrics assert m # we always have a name, so should always have metrics m.inc_hits() - return val.deferred.observe() + return val.deferred(key) + + callbacks = (callback,) if callback else () val2 = self.cache.get( key, _Sentinel.sentinel, callbacks=callbacks, update_metrics=update_metrics @@ -177,6 +181,73 @@ class DeferredCache(Generic[KT, VT]): else: return defer.succeed(val2) + def get_bulk( + self, + keys: Collection[KT], + callback: Optional[Callable[[], None]] = None, + ) -> Tuple[Dict[KT, VT], Optional["defer.Deferred[Dict[KT, VT]]"], Collection[KT]]: + """Bulk lookup of items in the cache. + + Returns: + A 3-tuple of: + 1. a dict of key/value of items already cached; + 2. a deferred that resolves to a dict of key/value of items + we're already fetching; and + 3. a collection of keys that don't appear in the previous two. + """ + + # The cached results + cached = {} + + # List of pending deferreds + pending = [] + + # Dict that gets filled out when the pending deferreds complete + pending_results = {} + + # List of keys that aren't in either cache + missing = [] + + callbacks = (callback,) if callback else () + + for key in keys: + # Check if its in the main cache. + immediate_value = self.cache.get( + key, + _Sentinel.sentinel, + callbacks=callbacks, + ) + if immediate_value is not _Sentinel.sentinel: + cached[key] = immediate_value + continue + + # Check if its in the pending cache + pending_value = self._pending_deferred_cache.get(key, _Sentinel.sentinel) + if pending_value is not _Sentinel.sentinel: + pending_value.add_invalidation_callback(key, callback) + + def completed_cb(value: VT, key: KT) -> VT: + pending_results[key] = value + return value + + # Add a callback to fill out `pending_results` when that completes + d = pending_value.deferred(key).addCallback(completed_cb, key) + pending.append(d) + continue + + # Not in either cache + missing.append(key) + + # If we've got pending deferreds, squash them into a single one that + # returns `pending_results`. + pending_deferred = None + if pending: + pending_deferred = defer.gatherResults( + pending, consumeErrors=True + ).addCallback(lambda _: pending_results) + + return (cached, pending_deferred, missing) + def get_immediate( self, key: KT, default: T, update_metrics: bool = True ) -> Union[VT, T]: @@ -218,84 +289,89 @@ class DeferredCache(Generic[KT, VT]): value: a deferred which will complete with a result to add to the cache callback: An optional callback to be called when the entry is invalidated """ - if not isinstance(value, defer.Deferred): - raise TypeError("not a Deferred") - - callbacks = [callback] if callback else [] self.check_thread() - existing_entry = self._pending_deferred_cache.pop(key, None) - if existing_entry: - existing_entry.invalidate() + self._pending_deferred_cache.pop(key, None) # XXX: why don't we invalidate the entry in `self.cache` yet? - # we can save a whole load of effort if the deferred is ready. - if value.called: - result = value.result - if not isinstance(result, failure.Failure): - self.cache.set(key, cast(VT, result), callbacks) - return value - # otherwise, we'll add an entry to the _pending_deferred_cache for now, # and add callbacks to add it to the cache properly later. + entry = CacheEntrySingle[KT, VT](value) + entry.add_invalidation_callback(key, callback) + self._pending_deferred_cache[key] = entry + deferred = entry.deferred(key).addCallbacks( + self._completed_callback, + self._error_callback, + callbackArgs=(entry, key), + errbackArgs=(entry, key), + ) - observable = ObservableDeferred(value, consumeErrors=True) - observer = observable.observe() - entry = CacheEntry(deferred=observable, callbacks=callbacks) + # we return a new Deferred which will be called before any subsequent observers. + return deferred - self._pending_deferred_cache[key] = entry + def start_bulk_input( + self, + keys: Collection[KT], + callback: Optional[Callable[[], None]] = None, + ) -> "CacheMultipleEntries[KT, VT]": + """Bulk set API for use when fetching multiple keys at once from the DB. - def compare_and_pop() -> bool: - """Check if our entry is still the one in _pending_deferred_cache, and - if so, pop it. - - Returns true if the entries matched. - """ - existing_entry = self._pending_deferred_cache.pop(key, None) - if existing_entry is entry: - return True - - # oops, the _pending_deferred_cache has been updated since - # we started our query, so we are out of date. - # - # Better put back whatever we took out. (We do it this way - # round, rather than peeking into the _pending_deferred_cache - # and then removing on a match, to make the common case faster) - if existing_entry is not None: - self._pending_deferred_cache[key] = existing_entry - - return False - - def cb(result: VT) -> None: - if compare_and_pop(): - self.cache.set(key, result, entry.callbacks) - else: - # we're not going to put this entry into the cache, so need - # to make sure that the invalidation callbacks are called. - # That was probably done when _pending_deferred_cache was - # updated, but it's possible that `set` was called without - # `invalidate` being previously called, in which case it may - # not have been. Either way, let's double-check now. - entry.invalidate() - - def eb(_fail: Failure) -> None: - compare_and_pop() - entry.invalidate() - - # once the deferred completes, we can move the entry from the - # _pending_deferred_cache to the real cache. - # - observer.addCallbacks(cb, eb) + Called *before* starting the fetch from the DB, and the caller *must* + call either `complete_bulk(..)` or `error_bulk(..)` on the return value. + """ - # we return a new Deferred which will be called before any subsequent observers. - return observable.observe() + entry = CacheMultipleEntries[KT, VT]() + entry.add_global_invalidation_callback(callback) + + for key in keys: + self._pending_deferred_cache[key] = entry + + return entry + + def _completed_callback( + self, value: VT, entry: "CacheEntry[KT, VT]", key: KT + ) -> VT: + """Called when a deferred is completed.""" + # We check if the current entry matches the entry associated with the + # deferred. If they don't match then it got invalidated. + current_entry = self._pending_deferred_cache.pop(key, None) + if current_entry is not entry: + if current_entry: + self._pending_deferred_cache[key] = current_entry + return value + + self.cache.set(key, value, entry.get_invalidation_callbacks(key)) + + return value + + def _error_callback( + self, + failure: Failure, + entry: "CacheEntry[KT, VT]", + key: KT, + ) -> Failure: + """Called when a deferred errors.""" + + # We check if the current entry matches the entry associated with the + # deferred. If they don't match then it got invalidated. + current_entry = self._pending_deferred_cache.pop(key, None) + if current_entry is not entry: + if current_entry: + self._pending_deferred_cache[key] = current_entry + return failure + + for cb in entry.get_invalidation_callbacks(key): + cb() + + return failure def prefill( self, key: KT, value: VT, callback: Optional[Callable[[], None]] = None ) -> None: - callbacks = [callback] if callback else [] + callbacks = (callback,) if callback else () self.cache.set(key, value, callbacks=callbacks) + self._pending_deferred_cache.pop(key, None) def invalidate(self, key: KT) -> None: """Delete a key, or tree of entries @@ -311,41 +387,129 @@ class DeferredCache(Generic[KT, VT]): self.cache.del_multi(key) # if we have a pending lookup for this key, remove it from the - # _pending_deferred_cache, which will (a) stop it being returned - # for future queries and (b) stop it being persisted as a proper entry + # _pending_deferred_cache, which will (a) stop it being returned for + # future queries and (b) stop it being persisted as a proper entry # in self.cache. entry = self._pending_deferred_cache.pop(key, None) - - # run the invalidation callbacks now, rather than waiting for the - # deferred to resolve. if entry: # _pending_deferred_cache.pop should either return a CacheEntry, or, in the # case of a TreeCache, a dict of keys to cache entries. Either way calling # iterate_tree_cache_entry on it will do the right thing. for entry in iterate_tree_cache_entry(entry): - entry.invalidate() + for cb in entry.get_invalidation_callbacks(key): + cb() def invalidate_all(self) -> None: self.check_thread() self.cache.clear() - for entry in self._pending_deferred_cache.values(): - entry.invalidate() + for key, entry in self._pending_deferred_cache.items(): + for cb in entry.get_invalidation_callbacks(key): + cb() + self._pending_deferred_cache.clear() -class CacheEntry: - __slots__ = ["deferred", "callbacks", "invalidated"] +class CacheEntry(Generic[KT, VT], metaclass=abc.ABCMeta): + """Abstract class for entries in `DeferredCache[KT, VT]`""" - def __init__( - self, deferred: ObservableDeferred, callbacks: Iterable[Callable[[], None]] - ): - self.deferred = deferred - self.callbacks = set(callbacks) - self.invalidated = False - - def invalidate(self) -> None: - if not self.invalidated: - self.invalidated = True - for callback in self.callbacks: - callback() - self.callbacks.clear() + @abc.abstractmethod + def deferred(self, key: KT) -> "defer.Deferred[VT]": + """Get a deferred that a caller can wait on to get the value at the + given key""" + ... + + @abc.abstractmethod + def add_invalidation_callback( + self, key: KT, callback: Optional[Callable[[], None]] + ) -> None: + """Add an invalidation callback""" + ... + + @abc.abstractmethod + def get_invalidation_callbacks(self, key: KT) -> Collection[Callable[[], None]]: + """Get all invalidation callbacks""" + ... + + +class CacheEntrySingle(CacheEntry[KT, VT]): + """An implementation of `CacheEntry` wrapping a deferred that results in a + single cache entry. + """ + + __slots__ = ["_deferred", "_callbacks"] + + def __init__(self, deferred: "defer.Deferred[VT]") -> None: + self._deferred = ObservableDeferred(deferred, consumeErrors=True) + self._callbacks: Set[Callable[[], None]] = set() + + def deferred(self, key: KT) -> "defer.Deferred[VT]": + return self._deferred.observe() + + def add_invalidation_callback( + self, key: KT, callback: Optional[Callable[[], None]] + ) -> None: + if callback is None: + return + + self._callbacks.add(callback) + + def get_invalidation_callbacks(self, key: KT) -> Collection[Callable[[], None]]: + return self._callbacks + + +class CacheMultipleEntries(CacheEntry[KT, VT]): + """Cache entry that is used for bulk lookups and insertions.""" + + __slots__ = ["_deferred", "_callbacks", "_global_callbacks"] + + def __init__(self) -> None: + self._deferred: Optional[ObservableDeferred[Dict[KT, VT]]] = None + self._callbacks: Dict[KT, Set[Callable[[], None]]] = {} + self._global_callbacks: Set[Callable[[], None]] = set() + + def deferred(self, key: KT) -> "defer.Deferred[VT]": + if not self._deferred: + self._deferred = ObservableDeferred(defer.Deferred(), consumeErrors=True) + return self._deferred.observe().addCallback(lambda res: res.get(key)) + + def add_invalidation_callback( + self, key: KT, callback: Optional[Callable[[], None]] + ) -> None: + if callback is None: + return + + self._callbacks.setdefault(key, set()).add(callback) + + def get_invalidation_callbacks(self, key: KT) -> Collection[Callable[[], None]]: + return self._callbacks.get(key, set()) | self._global_callbacks + + def add_global_invalidation_callback( + self, callback: Optional[Callable[[], None]] + ) -> None: + """Add a callback for when any keys get invalidated.""" + if callback is None: + return + + self._global_callbacks.add(callback) + + def complete_bulk( + self, + cache: DeferredCache[KT, VT], + result: Dict[KT, VT], + ) -> None: + """Called when there is a result""" + for key, value in result.items(): + cache._completed_callback(value, self, key) + + if self._deferred: + self._deferred.callback(result) + + def error_bulk( + self, cache: DeferredCache[KT, VT], keys: Collection[KT], failure: Failure + ) -> None: + """Called when bulk lookup failed.""" + for key in keys: + cache._error_callback(failure, self, key) + + if self._deferred: + self._deferred.errback(failure) diff --git a/synapse/util/caches/descriptors.py b/synapse/util/caches/descriptors.py index 867f315b2a..10aff4d04a 100644 --- a/synapse/util/caches/descriptors.py +++ b/synapse/util/caches/descriptors.py @@ -25,6 +25,7 @@ from typing import ( Generic, Hashable, Iterable, + List, Mapping, Optional, Sequence, @@ -73,8 +74,10 @@ class _CacheDescriptorBase: num_args: Optional[int], uncached_args: Optional[Collection[str]] = None, cache_context: bool = False, + name: Optional[str] = None, ): self.orig = orig + self.name = name or orig.__name__ arg_spec = inspect.getfullargspec(orig) all_args = arg_spec.args @@ -211,7 +214,7 @@ class LruCacheDescriptor(_CacheDescriptorBase): def __get__(self, obj: Optional[Any], owner: Optional[Type]) -> Callable[..., Any]: cache: LruCache[CacheKey, Any] = LruCache( - cache_name=self.orig.__name__, + cache_name=self.name, max_size=self.max_entries, ) @@ -241,7 +244,7 @@ class LruCacheDescriptor(_CacheDescriptorBase): wrapped = cast(_CachedFunction, _wrapped) wrapped.cache = cache - obj.__dict__[self.orig.__name__] = wrapped + obj.__dict__[self.name] = wrapped return wrapped @@ -301,12 +304,14 @@ class DeferredCacheDescriptor(_CacheDescriptorBase): cache_context: bool = False, iterable: bool = False, prune_unread_entries: bool = True, + name: Optional[str] = None, ): super().__init__( orig, num_args=num_args, uncached_args=uncached_args, cache_context=cache_context, + name=name, ) if tree and self.num_args < 2: @@ -321,7 +326,7 @@ class DeferredCacheDescriptor(_CacheDescriptorBase): def __get__(self, obj: Optional[Any], owner: Optional[Type]) -> Callable[..., Any]: cache: DeferredCache[CacheKey, Any] = DeferredCache( - name=self.orig.__name__, + name=self.name, max_entries=self.max_entries, tree=self.tree, iterable=self.iterable, @@ -372,7 +377,7 @@ class DeferredCacheDescriptor(_CacheDescriptorBase): wrapped.cache = cache wrapped.num_args = self.num_args - obj.__dict__[self.orig.__name__] = wrapped + obj.__dict__[self.name] = wrapped return wrapped @@ -393,6 +398,7 @@ class DeferredCacheListDescriptor(_CacheDescriptorBase): cached_method_name: str, list_name: str, num_args: Optional[int] = None, + name: Optional[str] = None, ): """ Args: @@ -403,7 +409,7 @@ class DeferredCacheListDescriptor(_CacheDescriptorBase): but including list_name) to use as cache keys. Defaults to all named args of the function. """ - super().__init__(orig, num_args=num_args, uncached_args=None) + super().__init__(orig, num_args=num_args, uncached_args=None, name=name) self.list_name = list_name @@ -435,16 +441,6 @@ class DeferredCacheListDescriptor(_CacheDescriptorBase): keyargs = [arg_dict[arg_nm] for arg_nm in self.arg_names] list_args = arg_dict[self.list_name] - results = {} - - def update_results_dict(res: Any, arg: Hashable) -> None: - results[arg] = res - - # list of deferreds to wait for - cached_defers = [] - - missing = set() - # If the cache takes a single arg then that is used as the key, # otherwise a tuple is used. if num_args == 1: @@ -452,6 +448,9 @@ class DeferredCacheListDescriptor(_CacheDescriptorBase): def arg_to_cache_key(arg: Hashable) -> Hashable: return arg + def cache_key_to_arg(key: tuple) -> Hashable: + return key + else: keylist = list(keyargs) @@ -459,58 +458,53 @@ class DeferredCacheListDescriptor(_CacheDescriptorBase): keylist[self.list_pos] = arg return tuple(keylist) - for arg in list_args: - try: - res = cache.get(arg_to_cache_key(arg), callback=invalidate_callback) - if not res.called: - res.addCallback(update_results_dict, arg) - cached_defers.append(res) - else: - results[arg] = res.result - except KeyError: - missing.add(arg) + def cache_key_to_arg(key: tuple) -> Hashable: + return key[self.list_pos] + + cache_keys = [arg_to_cache_key(arg) for arg in list_args] + immediate_results, pending_deferred, missing = cache.get_bulk( + cache_keys, callback=invalidate_callback + ) + + results = {cache_key_to_arg(key): v for key, v in immediate_results.items()} + + cached_defers: List["defer.Deferred[Any]"] = [] + if pending_deferred: + + def update_results(r: Dict) -> None: + for k, v in r.items(): + results[cache_key_to_arg(k)] = v + + pending_deferred.addCallback(update_results) + cached_defers.append(pending_deferred) if missing: - # we need a deferred for each entry in the list, - # which we put in the cache. Each deferred resolves with the - # relevant result for that key. - deferreds_map = {} - for arg in missing: - deferred: "defer.Deferred[Any]" = defer.Deferred() - deferreds_map[arg] = deferred - key = arg_to_cache_key(arg) - cached_defers.append( - cache.set(key, deferred, callback=invalidate_callback) - ) + cache_entry = cache.start_bulk_input(missing, invalidate_callback) def complete_all(res: Dict[Hashable, Any]) -> None: - # the wrapped function has completed. It returns a dict. - # We can now update our own result map, and then resolve the - # observable deferreds in the cache. - for e, d1 in deferreds_map.items(): - val = res.get(e, None) - # make sure we update the results map before running the - # deferreds, because as soon as we run the last deferred, the - # gatherResults() below will complete and return the result - # dict to our caller. - results[e] = val - d1.callback(val) + missing_results = {} + for key in missing: + arg = cache_key_to_arg(key) + val = res.get(arg, None) + + results[arg] = val + missing_results[key] = val + + cache_entry.complete_bulk(cache, missing_results) def errback_all(f: Failure) -> None: - # the wrapped function has failed. Propagate the failure into - # the cache, which will invalidate the entry, and cause the - # relevant cached_deferreds to fail, which will propagate the - # failure to our caller. - for d1 in deferreds_map.values(): - d1.errback(f) + cache_entry.error_bulk(cache, missing, f) args_to_call = dict(arg_dict) - args_to_call[self.list_name] = missing + args_to_call[self.list_name] = { + cache_key_to_arg(key) for key in missing + } # dispatch the call, and attach the two handlers - defer.maybeDeferred( + missing_d = defer.maybeDeferred( preserve_fn(self.orig), **args_to_call ).addCallbacks(complete_all, errback_all) + cached_defers.append(missing_d) if cached_defers: d = defer.gatherResults(cached_defers, consumeErrors=True).addCallbacks( @@ -525,7 +519,7 @@ class DeferredCacheListDescriptor(_CacheDescriptorBase): else: return defer.succeed(results) - obj.__dict__[self.orig.__name__] = wrapped + obj.__dict__[self.name] = wrapped return wrapped @@ -577,6 +571,7 @@ def cached( cache_context: bool = False, iterable: bool = False, prune_unread_entries: bool = True, + name: Optional[str] = None, ) -> Callable[[F], _CachedFunction[F]]: func = lambda orig: DeferredCacheDescriptor( orig, @@ -587,13 +582,18 @@ def cached( cache_context=cache_context, iterable=iterable, prune_unread_entries=prune_unread_entries, + name=name, ) return cast(Callable[[F], _CachedFunction[F]], func) def cachedList( - *, cached_method_name: str, list_name: str, num_args: Optional[int] = None + *, + cached_method_name: str, + list_name: str, + num_args: Optional[int] = None, + name: Optional[str] = None, ) -> Callable[[F], _CachedFunction[F]]: """Creates a descriptor that wraps a function in a `DeferredCacheListDescriptor`. @@ -628,6 +628,7 @@ def cachedList( cached_method_name=cached_method_name, list_name=list_name, num_args=num_args, + name=name, ) return cast(Callable[[F], _CachedFunction[F]], func) diff --git a/synapse/util/caches/treecache.py b/synapse/util/caches/treecache.py index c1b8ec0c73..fec31da2b6 100644 --- a/synapse/util/caches/treecache.py +++ b/synapse/util/caches/treecache.py @@ -135,6 +135,9 @@ class TreeCache: def values(self): return iterate_tree_cache_entry(self.root) + def items(self): + return iterate_tree_cache_items((), self.root) + def __len__(self) -> int: return self.size diff --git a/synapse/util/ratelimitutils.py b/synapse/util/ratelimitutils.py index 6394cc39ac..f678b52cb4 100644 --- a/synapse/util/ratelimitutils.py +++ b/synapse/util/ratelimitutils.py @@ -18,6 +18,8 @@ import logging import typing from typing import Any, DefaultDict, Iterator, List, Set +from prometheus_client.core import Counter + from twisted.internet import defer from synapse.api.errors import LimitExceededError @@ -27,6 +29,8 @@ from synapse.logging.context import ( make_deferred_yieldable, run_in_background, ) +from synapse.logging.opentracing import start_active_span +from synapse.metrics import Histogram, LaterGauge from synapse.util import Clock if typing.TYPE_CHECKING: @@ -35,6 +39,32 @@ if typing.TYPE_CHECKING: logger = logging.getLogger(__name__) +# Track how much the ratelimiter is affecting requests +rate_limit_sleep_counter = Counter("synapse_rate_limit_sleep", "") +rate_limit_reject_counter = Counter("synapse_rate_limit_reject", "") +queue_wait_timer = Histogram( + "synapse_rate_limit_queue_wait_time_seconds", + "sec", + [], + buckets=( + 0.005, + 0.01, + 0.025, + 0.05, + 0.1, + 0.25, + 0.5, + 0.75, + 1.0, + 2.5, + 5.0, + 10.0, + 20.0, + "+Inf", + ), +) + + class FederationRateLimiter: def __init__(self, clock: Clock, config: FederationRatelimitSettings): def new_limiter() -> "_PerHostRatelimiter": @@ -44,6 +74,27 @@ class FederationRateLimiter: str, "_PerHostRatelimiter" ] = collections.defaultdict(new_limiter) + # We track the number of affected hosts per time-period so we can + # differentiate one really noisy homeserver from a general + # ratelimit tuning problem across the federation. + LaterGauge( + "synapse_rate_limit_sleep_affected_hosts", + "Number of hosts that had requests put to sleep", + [], + lambda: sum( + ratelimiter.should_sleep() for ratelimiter in self.ratelimiters.values() + ), + ) + LaterGauge( + "synapse_rate_limit_reject_affected_hosts", + "Number of hosts that had requests rejected", + [], + lambda: sum( + ratelimiter.should_reject() + for ratelimiter in self.ratelimiters.values() + ), + ) + def ratelimit(self, host: str) -> "_GeneratorContextManager[defer.Deferred[None]]": """Used to ratelimit an incoming request from a given host @@ -59,7 +110,7 @@ class FederationRateLimiter: Returns: context manager which returns a deferred. """ - return self.ratelimiters[host].ratelimit() + return self.ratelimiters[host].ratelimit(host) class _PerHostRatelimiter: @@ -94,19 +145,42 @@ class _PerHostRatelimiter: self.request_times: List[int] = [] @contextlib.contextmanager - def ratelimit(self) -> "Iterator[defer.Deferred[None]]": + def ratelimit(self, host: str) -> "Iterator[defer.Deferred[None]]": # `contextlib.contextmanager` takes a generator and turns it into a # context manager. The generator should only yield once with a value # to be returned by manager. # Exceptions will be reraised at the yield. + self.host = host + request_id = object() - ret = self._on_enter(request_id) + # Ideally we'd use `Deferred.fromCoroutine()` here, to save on redundant + # type-checking, but we'd need Twisted >= 21.2. + ret = defer.ensureDeferred(self._on_enter_with_tracing(request_id)) try: yield ret finally: self._on_exit(request_id) + def should_reject(self) -> bool: + """ + Whether to reject the request if we already have too many queued up + (either sleeping or in the ready queue). + """ + queue_size = len(self.ready_request_queue) + len(self.sleeping_requests) + return queue_size > self.reject_limit + + def should_sleep(self) -> bool: + """ + Whether to sleep the request if we already have too many requests coming + through within the window. + """ + return len(self.request_times) > self.sleep_limit + + async def _on_enter_with_tracing(self, request_id: object) -> None: + with start_active_span("ratelimit wait"), queue_wait_timer.time(): + await self._on_enter(request_id) + def _on_enter(self, request_id: object) -> "defer.Deferred[None]": time_now = self.clock.time_msec() @@ -117,8 +191,9 @@ class _PerHostRatelimiter: # reject the request if we already have too many queued up (either # sleeping or in the ready queue). - queue_size = len(self.ready_request_queue) + len(self.sleeping_requests) - if queue_size > self.reject_limit: + if self.should_reject(): + logger.debug("Ratelimiter(%s): rejecting request", self.host) + rate_limit_reject_counter.inc() raise LimitExceededError( retry_after_ms=int(self.window_size / self.sleep_limit) ) @@ -130,7 +205,8 @@ class _PerHostRatelimiter: queue_defer: defer.Deferred[None] = defer.Deferred() self.ready_request_queue[request_id] = queue_defer logger.info( - "Ratelimiter: queueing request (queue now %i items)", + "Ratelimiter(%s): queueing request (queue now %i items)", + self.host, len(self.ready_request_queue), ) @@ -139,19 +215,28 @@ class _PerHostRatelimiter: return defer.succeed(None) logger.debug( - "Ratelimit [%s]: len(self.request_times)=%d", + "Ratelimit(%s) [%s]: len(self.request_times)=%d", + self.host, id(request_id), len(self.request_times), ) - if len(self.request_times) > self.sleep_limit: - logger.debug("Ratelimiter: sleeping request for %f sec", self.sleep_sec) + if self.should_sleep(): + logger.debug( + "Ratelimiter(%s) [%s]: sleeping request for %f sec", + self.host, + id(request_id), + self.sleep_sec, + ) + rate_limit_sleep_counter.inc() ret_defer = run_in_background(self.clock.sleep, self.sleep_sec) self.sleeping_requests.add(request_id) def on_wait_finished(_: Any) -> "defer.Deferred[None]": - logger.debug("Ratelimit [%s]: Finished sleeping", id(request_id)) + logger.debug( + "Ratelimit(%s) [%s]: Finished sleeping", self.host, id(request_id) + ) self.sleeping_requests.discard(request_id) queue_defer = queue_request() return queue_defer @@ -161,7 +246,9 @@ class _PerHostRatelimiter: ret_defer = queue_request() def on_start(r: object) -> object: - logger.debug("Ratelimit [%s]: Processing req", id(request_id)) + logger.debug( + "Ratelimit(%s) [%s]: Processing req", self.host, id(request_id) + ) self.current_processing.add(request_id) return r @@ -183,7 +270,7 @@ class _PerHostRatelimiter: return make_deferred_yieldable(ret_defer) def _on_exit(self, request_id: object) -> None: - logger.debug("Ratelimit [%s]: Processed req", id(request_id)) + logger.debug("Ratelimit(%s) [%s]: Processed req", self.host, id(request_id)) self.current_processing.discard(request_id) try: # start processing the next item on the queue. diff --git a/tests/api/test_auth.py b/tests/api/test_auth.py index dfcfaf79b6..e0f363555b 100644 --- a/tests/api/test_auth.py +++ b/tests/api/test_auth.py @@ -284,10 +284,13 @@ class AuthTestCase(unittest.HomeserverTestCase): TokenLookupResult( user_id="@baldrick:matrix.org", device_id="device", + token_id=5, token_owner="@admin:matrix.org", + token_used=True, ) ) self.store.insert_client_ip = simple_async_mock(None) + self.store.mark_access_token_as_used = simple_async_mock(None) request = Mock(args={}) request.getClientAddress.return_value.host = "127.0.0.1" request.args[b"access_token"] = [self.test_token] @@ -301,10 +304,13 @@ class AuthTestCase(unittest.HomeserverTestCase): TokenLookupResult( user_id="@baldrick:matrix.org", device_id="device", + token_id=5, token_owner="@admin:matrix.org", + token_used=True, ) ) self.store.insert_client_ip = simple_async_mock(None) + self.store.mark_access_token_as_used = simple_async_mock(None) request = Mock(args={}) request.getClientAddress.return_value.host = "127.0.0.1" request.args[b"access_token"] = [self.test_token] @@ -347,7 +353,7 @@ class AuthTestCase(unittest.HomeserverTestCase): serialized = macaroon.serialize() user_info = self.get_success(self.auth.get_user_by_access_token(serialized)) - self.assertEqual(user_id, user_info.user_id) + self.assertEqual(user_id, user_info.user.to_string()) self.assertTrue(user_info.is_guest) self.store.get_user_by_id.assert_called_with(user_id) diff --git a/tests/events/test_presence_router.py b/tests/events/test_presence_router.py index ffc3012a86..685a9a6d52 100644 --- a/tests/events/test_presence_router.py +++ b/tests/events/test_presence_router.py @@ -141,10 +141,6 @@ class PresenceRouterTestCase(FederatingHomeserverTestCase): hs = self.setup_test_homeserver( federation_transport_client=fed_transport_client, ) - # Load the modules into the homeserver - module_api = hs.get_module_api() - for module, config in hs.config.modules.loaded_modules: - module(config=config, api=module_api) load_legacy_presence_router(hs) diff --git a/tests/federation/test_federation_sender.py b/tests/federation/test_federation_sender.py index 01a1db6115..a5aa500ef8 100644 --- a/tests/federation/test_federation_sender.py +++ b/tests/federation/test_federation_sender.py @@ -173,17 +173,24 @@ class FederationSenderDevicesTestCases(HomeserverTestCase): return c def prepare(self, reactor, clock, hs): - # stub out `get_rooms_for_user` and `get_users_in_room` so that the + test_room_id = "!room:host1" + + # stub out `get_rooms_for_user` and `get_current_hosts_in_room` so that the # server thinks the user shares a room with `@user2:host2` def get_rooms_for_user(user_id): - return defer.succeed({"!room:host1"}) + return defer.succeed({test_room_id}) hs.get_datastores().main.get_rooms_for_user = get_rooms_for_user - def get_users_in_room(room_id): - return defer.succeed({"@user2:host2"}) + async def get_current_hosts_in_room(room_id): + if room_id == test_room_id: + return ["host2"] + + # TODO: We should fail the test when we encounter an unxpected room ID. + # We can't just use `self.fail(...)` here because the app code is greedy + # with `Exception` and will catch it before the test can see it. - hs.get_datastores().main.get_users_in_room = get_users_in_room + hs.get_datastores().main.get_current_hosts_in_room = get_current_hosts_in_room # whenever send_transaction is called, record the edu data self.edus = [] diff --git a/tests/handlers/test_deactivate_account.py b/tests/handlers/test_deactivate_account.py index ff9f2e8edb..7b9b711521 100644 --- a/tests/handlers/test_deactivate_account.py +++ b/tests/handlers/test_deactivate_account.py @@ -11,11 +11,11 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. -from typing import Any, Dict from twisted.test.proto_helpers import MemoryReactor from synapse.api.constants import AccountDataTypes +from synapse.push.baserules import PushRule from synapse.push.rulekinds import PRIORITY_CLASS_MAP from synapse.rest import admin from synapse.rest.client import account, login @@ -130,12 +130,12 @@ class DeactivateAccountTestCase(HomeserverTestCase): ), ) - def _is_custom_rule(self, push_rule: Dict[str, Any]) -> bool: + def _is_custom_rule(self, push_rule: PushRule) -> bool: """ Default rules start with a dot: such as .m.rule and .im.vector. This function returns true iff a rule is custom (not default). """ - return "/." not in push_rule["rule_id"] + return "/." not in push_rule.rule_id def test_push_rules_deleted_upon_account_deactivation(self) -> None: """ @@ -157,22 +157,21 @@ class DeactivateAccountTestCase(HomeserverTestCase): ) # Test the rule exists - push_rules = self.get_success(self._store.get_push_rules_for_user(self.user)) + filtered_push_rules = self.get_success( + self._store.get_push_rules_for_user(self.user) + ) # Filter out default rules; we don't care - push_rules = list(filter(self._is_custom_rule, push_rules)) + push_rules = [r for r, _ in filtered_push_rules if self._is_custom_rule(r)] # Check our rule made it self.assertEqual( push_rules, [ - { - "user_name": "@user:test", - "rule_id": "personal.override.rule1", - "priority_class": 5, - "priority": 0, - "conditions": [], - "actions": [], - "default": False, - } + PushRule( + rule_id="personal.override.rule1", + priority_class=5, + conditions=[], + actions=[], + ) ], push_rules, ) @@ -180,9 +179,11 @@ class DeactivateAccountTestCase(HomeserverTestCase): # Request the deactivation of our account self._deactivate_my_account() - push_rules = self.get_success(self._store.get_push_rules_for_user(self.user)) + filtered_push_rules = self.get_success( + self._store.get_push_rules_for_user(self.user) + ) # Filter out default rules; we don't care - push_rules = list(filter(self._is_custom_rule, push_rules)) + push_rules = [r for r, _ in filtered_push_rules if self._is_custom_rule(r)] # Check our rule no longer exists self.assertEqual(push_rules, [], push_rules) @@ -321,3 +322,18 @@ class DeactivateAccountTestCase(HomeserverTestCase): ) ), ) + + def test_deactivate_account_needs_auth(self) -> None: + """ + Tests that making a request to /deactivate with an empty body + succeeds in starting the user-interactive auth flow. + """ + req = self.make_request( + "POST", + "account/deactivate", + {}, + access_token=self.token, + ) + + self.assertEqual(req.code, 401, req) + self.assertEqual(req.json_body["flows"], [{"stages": ["m.login.password"]}]) diff --git a/tests/handlers/test_password_providers.py b/tests/handlers/test_password_providers.py index 4c62449c89..75934b1707 100644 --- a/tests/handlers/test_password_providers.py +++ b/tests/handlers/test_password_providers.py @@ -21,7 +21,6 @@ from unittest.mock import Mock import synapse from synapse.api.constants import LoginType from synapse.api.errors import Codes -from synapse.handlers.auth import load_legacy_password_auth_providers from synapse.module_api import ModuleApi from synapse.rest.client import account, devices, login, logout, register from synapse.types import JsonDict, UserID @@ -167,16 +166,6 @@ class PasswordAuthProviderTests(unittest.HomeserverTestCase): mock_password_provider.reset_mock() super().setUp() - def make_homeserver(self, reactor, clock): - hs = self.setup_test_homeserver() - # Load the modules into the homeserver - module_api = hs.get_module_api() - for module, config in hs.config.modules.loaded_modules: - module(config=config, api=module_api) - load_legacy_password_auth_providers(hs) - - return hs - @override_config(legacy_providers_config(LegacyPasswordOnlyAuthProvider)) def test_password_only_auth_progiver_login_legacy(self): self.password_only_auth_provider_login_test_body() diff --git a/tests/handlers/test_register.py b/tests/handlers/test_register.py index 23f35d5bf5..86b3d51975 100644 --- a/tests/handlers/test_register.py +++ b/tests/handlers/test_register.py @@ -22,7 +22,6 @@ from synapse.api.errors import ( ResourceLimitError, SynapseError, ) -from synapse.events.spamcheck import load_legacy_spam_checkers from synapse.spam_checker_api import RegistrationBehaviour from synapse.types import RoomAlias, RoomID, UserID, create_requester @@ -144,12 +143,6 @@ class RegistrationTestCase(unittest.HomeserverTestCase): config=hs_config, federation_client=self.mock_federation_client ) - load_legacy_spam_checkers(hs) - - module_api = hs.get_module_api() - for module, config in hs.config.modules.loaded_modules: - module(config=config, api=module_api) - return hs def prepare(self, reactor, clock, hs): diff --git a/tests/handlers/test_room_member.py b/tests/handlers/test_room_member.py index b4e1405aee..1d13ed1e88 100644 --- a/tests/handlers/test_room_member.py +++ b/tests/handlers/test_room_member.py @@ -14,7 +14,7 @@ from synapse.server import HomeServer from synapse.types import UserID, create_requester from synapse.util import Clock -from tests.replication._base import RedisMultiWorkerStreamTestCase +from tests.replication._base import BaseMultiWorkerStreamTestCase from tests.server import make_request from tests.test_utils import make_awaitable from tests.unittest import FederatingHomeserverTestCase, override_config @@ -216,7 +216,7 @@ class TestJoinsLimitedByPerRoomRateLimiter(FederatingHomeserverTestCase): # - trying to remote-join again. -class TestReplicatedJoinsLimitedByPerRoomRateLimiter(RedisMultiWorkerStreamTestCase): +class TestReplicatedJoinsLimitedByPerRoomRateLimiter(BaseMultiWorkerStreamTestCase): servlets = [ synapse.rest.admin.register_servlets, synapse.rest.client.login.register_servlets, diff --git a/tests/handlers/test_typing.py b/tests/handlers/test_typing.py index 7af1333126..8adba29d7f 100644 --- a/tests/handlers/test_typing.py +++ b/tests/handlers/test_typing.py @@ -25,7 +25,7 @@ from synapse.api.constants import EduTypes from synapse.api.errors import AuthError from synapse.federation.transport.server import TransportLayerServer from synapse.server import HomeServer -from synapse.types import JsonDict, UserID, create_requester +from synapse.types import JsonDict, Requester, UserID, create_requester from synapse.util import Clock from tests import unittest @@ -117,8 +117,10 @@ class TypingNotificationsTestCase(unittest.HomeserverTestCase): self.room_members = [] - async def check_user_in_room(room_id: str, user_id: str) -> None: - if user_id not in [u.to_string() for u in self.room_members]: + async def check_user_in_room(room_id: str, requester: Requester) -> None: + if requester.user.to_string() not in [ + u.to_string() for u in self.room_members + ]: raise AuthError(401, "User is not in the room") return None diff --git a/tests/module_api/test_api.py b/tests/module_api/test_api.py index 106159fa65..02cef6f876 100644 --- a/tests/module_api/test_api.py +++ b/tests/module_api/test_api.py @@ -30,7 +30,6 @@ from tests.replication._base import BaseMultiWorkerStreamTestCase from tests.test_utils import simple_async_mock from tests.test_utils.event_injection import inject_member_event from tests.unittest import HomeserverTestCase, override_config -from tests.utils import USE_POSTGRES_FOR_TESTS class ModuleApiTestCase(HomeserverTestCase): @@ -738,11 +737,6 @@ class ModuleApiTestCase(HomeserverTestCase): class ModuleApiWorkerTestCase(BaseMultiWorkerStreamTestCase): """For testing ModuleApi functionality in a multi-worker setup""" - # Testing stream ID replication from the main to worker processes requires postgres - # (due to needing `MultiWriterIdGenerator`). - if not USE_POSTGRES_FOR_TESTS: - skip = "Requires Postgres" - servlets = [ admin.register_servlets, login.register_servlets, @@ -752,7 +746,6 @@ class ModuleApiWorkerTestCase(BaseMultiWorkerStreamTestCase): def default_config(self): conf = super().default_config() - conf["redis"] = {"enabled": "true"} conf["stream_writers"] = {"presence": ["presence_writer"]} conf["instance_map"] = { "presence_writer": {"host": "testserv", "port": 1001}, diff --git a/tests/replication/_base.py b/tests/replication/_base.py index 970d5e533b..ce53f808db 100644 --- a/tests/replication/_base.py +++ b/tests/replication/_base.py @@ -24,11 +24,11 @@ from synapse.http.site import SynapseRequest, SynapseSite from synapse.replication.http import ReplicationRestResource from synapse.replication.tcp.client import ReplicationDataHandler from synapse.replication.tcp.handler import ReplicationCommandHandler -from synapse.replication.tcp.protocol import ClientReplicationStreamProtocol -from synapse.replication.tcp.resource import ( - ReplicationStreamProtocolFactory, +from synapse.replication.tcp.protocol import ( + ClientReplicationStreamProtocol, ServerReplicationStreamProtocol, ) +from synapse.replication.tcp.resource import ReplicationStreamProtocolFactory from synapse.server import HomeServer from tests import unittest @@ -220,15 +220,34 @@ class BaseStreamTestCase(unittest.HomeserverTestCase): class BaseMultiWorkerStreamTestCase(unittest.HomeserverTestCase): """Base class for tests running multiple workers. + Enables Redis, providing a fake Redis server. + Automatically handle HTTP replication requests from workers to master, unlike `BaseStreamTestCase`. """ + if not hiredis: + skip = "Requires hiredis" + + if not USE_POSTGRES_FOR_TESTS: + # Redis replication only takes place on Postgres + skip = "Requires Postgres" + + def default_config(self) -> Dict[str, Any]: + """ + Overrides the default config to enable Redis. + Even if the test only uses make_worker_hs, the main process needs Redis + enabled otherwise it won't create a Fake Redis server to listen on the + Redis port and accept fake TCP connections. + """ + base = super().default_config() + base["redis"] = {"enabled": True} + return base + def setUp(self): super().setUp() # build a replication server - self.server_factory = ReplicationStreamProtocolFactory(self.hs) self.streamer = self.hs.get_replication_streamer() # Fake in memory Redis server that servers can connect to. @@ -247,15 +266,14 @@ class BaseMultiWorkerStreamTestCase(unittest.HomeserverTestCase): # handling inbound HTTP requests to that instance. self._hs_to_site = {self.hs: self.site} - if self.hs.config.redis.redis_enabled: - # Handle attempts to connect to fake redis server. - self.reactor.add_tcp_client_callback( - "localhost", - 6379, - self.connect_any_redis_attempts, - ) + # Handle attempts to connect to fake redis server. + self.reactor.add_tcp_client_callback( + "localhost", + 6379, + self.connect_any_redis_attempts, + ) - self.hs.get_replication_command_handler().start_replication(self.hs) + self.hs.get_replication_command_handler().start_replication(self.hs) # When we see a connection attempt to the master replication listener we # automatically set up the connection. This is so that tests don't @@ -339,27 +357,6 @@ class BaseMultiWorkerStreamTestCase(unittest.HomeserverTestCase): store = worker_hs.get_datastores().main store.db_pool._db_pool = self.database_pool._db_pool - # Set up TCP replication between master and the new worker if we don't - # have Redis support enabled. - if not worker_hs.config.redis.redis_enabled: - repl_handler = ReplicationCommandHandler(worker_hs) - client = ClientReplicationStreamProtocol( - worker_hs, - "client", - "test", - self.clock, - repl_handler, - ) - server = self.server_factory.buildProtocol( - IPv4Address("TCP", "127.0.0.1", 0) - ) - - client_transport = FakeTransport(server, self.reactor) - client.makeConnection(client_transport) - - server_transport = FakeTransport(client, self.reactor) - server.makeConnection(server_transport) - # Set up a resource for the worker resource = ReplicationRestResource(worker_hs) @@ -378,8 +375,7 @@ class BaseMultiWorkerStreamTestCase(unittest.HomeserverTestCase): reactor=self.reactor, ) - if worker_hs.config.redis.redis_enabled: - worker_hs.get_replication_command_handler().start_replication(worker_hs) + worker_hs.get_replication_command_handler().start_replication(worker_hs) return worker_hs @@ -582,27 +578,3 @@ class FakeRedisPubSubProtocol(Protocol): def connectionLost(self, reason): self._server.remove_subscriber(self) - - -class RedisMultiWorkerStreamTestCase(BaseMultiWorkerStreamTestCase): - """ - A test case that enables Redis, providing a fake Redis server. - """ - - if not hiredis: - skip = "Requires hiredis" - - if not USE_POSTGRES_FOR_TESTS: - # Redis replication only takes place on Postgres - skip = "Requires Postgres" - - def default_config(self) -> Dict[str, Any]: - """ - Overrides the default config to enable Redis. - Even if the test only uses make_worker_hs, the main process needs Redis - enabled otherwise it won't create a Fake Redis server to listen on the - Redis port and accept fake TCP connections. - """ - base = super().default_config() - base["redis"] = {"enabled": True} - return base diff --git a/tests/replication/tcp/test_handler.py b/tests/replication/tcp/test_handler.py index e6a19eafd5..1e299d2d67 100644 --- a/tests/replication/tcp/test_handler.py +++ b/tests/replication/tcp/test_handler.py @@ -12,10 +12,10 @@ # See the License for the specific language governing permissions and # limitations under the License. -from tests.replication._base import RedisMultiWorkerStreamTestCase +from tests.replication._base import BaseMultiWorkerStreamTestCase -class ChannelsTestCase(RedisMultiWorkerStreamTestCase): +class ChannelsTestCase(BaseMultiWorkerStreamTestCase): def test_subscribed_to_enough_redis_channels(self) -> None: # The default main process is subscribed to the USER_IP channel. self.assertCountEqual( diff --git a/tests/replication/test_sharded_event_persister.py b/tests/replication/test_sharded_event_persister.py index a7ca68069e..541d390286 100644 --- a/tests/replication/test_sharded_event_persister.py +++ b/tests/replication/test_sharded_event_persister.py @@ -20,7 +20,6 @@ from synapse.storage.util.id_generators import MultiWriterIdGenerator from tests.replication._base import BaseMultiWorkerStreamTestCase from tests.server import make_request -from tests.utils import USE_POSTGRES_FOR_TESTS logger = logging.getLogger(__name__) @@ -28,11 +27,6 @@ logger = logging.getLogger(__name__) class EventPersisterShardTestCase(BaseMultiWorkerStreamTestCase): """Checks event persisting sharding works""" - # Event persister sharding requires postgres (due to needing - # `MultiWriterIdGenerator`). - if not USE_POSTGRES_FOR_TESTS: - skip = "Requires Postgres" - servlets = [ admin.register_servlets_for_client_rest_resource, room.register_servlets, @@ -50,7 +44,6 @@ class EventPersisterShardTestCase(BaseMultiWorkerStreamTestCase): def default_config(self): conf = super().default_config() - conf["redis"] = {"enabled": "true"} conf["stream_writers"] = {"events": ["worker1", "worker2"]} conf["instance_map"] = { "worker1": {"host": "testserv", "port": 1001}, diff --git a/tests/rest/admin/test_event_reports.py b/tests/rest/admin/test_event_reports.py index fbc490f46d..8a4e5c3f77 100644 --- a/tests/rest/admin/test_event_reports.py +++ b/tests/rest/admin/test_event_reports.py @@ -410,6 +410,33 @@ class EventReportsTestCase(unittest.HomeserverTestCase): self.assertIn("score", c) self.assertIn("reason", c) + def test_count_correct_despite_table_deletions(self) -> None: + """ + Tests that the count matches the number of rows, even if rows in joined tables + are missing. + """ + + # Delete rows from room_stats_state for one of our rooms. + self.get_success( + self.hs.get_datastores().main.db_pool.simple_delete( + "room_stats_state", {"room_id": self.room_id1}, desc="_" + ) + ) + + channel = self.make_request( + "GET", + self.url, + access_token=self.admin_user_tok, + ) + + self.assertEqual(200, channel.code, msg=channel.json_body) + # The 'total' field is 10 because only 10 reports will actually + # be retrievable since we deleted the rows in the room_stats_state + # table. + self.assertEqual(channel.json_body["total"], 10) + # This is consistent with the number of rows actually returned. + self.assertEqual(len(channel.json_body["event_reports"]), 10) + class EventReportDetailTestCase(unittest.HomeserverTestCase): servlets = [ diff --git a/tests/rest/admin/test_room.py b/tests/rest/admin/test_room.py index dd5000679a..fd6da557c1 100644 --- a/tests/rest/admin/test_room.py +++ b/tests/rest/admin/test_room.py @@ -1633,6 +1633,7 @@ class RoomTestCase(unittest.HomeserverTestCase): self.assertIn("history_visibility", channel.json_body) self.assertIn("state_events", channel.json_body) self.assertIn("room_type", channel.json_body) + self.assertIn("forgotten", channel.json_body) self.assertEqual(room_id_1, channel.json_body["room_id"]) def test_single_room_devices(self) -> None: diff --git a/tests/rest/admin/test_server_notice.py b/tests/rest/admin/test_server_notice.py index 81e125e27d..a2f347f666 100644 --- a/tests/rest/admin/test_server_notice.py +++ b/tests/rest/admin/test_server_notice.py @@ -159,6 +159,62 @@ class ServerNoticeTestCase(unittest.HomeserverTestCase): self.assertEqual(Codes.UNKNOWN, channel.json_body["errcode"]) self.assertEqual("'msgtype' not in content", channel.json_body["error"]) + @override_config( + { + "server_notices": { + "system_mxid_localpart": "notices", + "system_mxid_avatar_url": "somthingwrong", + }, + "max_avatar_size": "10M", + } + ) + def test_invalid_avatar_url(self) -> None: + """If avatar url in homeserver.yaml is invalid and + "check avatar size and mime type" is set, an error is returned. + TODO: Should be checked when reading the configuration.""" + channel = self.make_request( + "POST", + self.url, + access_token=self.admin_user_tok, + content={ + "user_id": self.other_user, + "content": {"msgtype": "m.text", "body": "test msg"}, + }, + ) + + self.assertEqual(500, channel.code, msg=channel.json_body) + self.assertEqual(Codes.UNKNOWN, channel.json_body["errcode"]) + + @override_config( + { + "server_notices": { + "system_mxid_localpart": "notices", + "system_mxid_display_name": "test display name", + "system_mxid_avatar_url": None, + }, + "max_avatar_size": "10M", + } + ) + def test_displayname_is_set_avatar_is_none(self) -> None: + """ + Tests that sending a server notices is successfully, + if a display_name is set, avatar_url is `None` and + "check avatar size and mime type" is set. + """ + channel = self.make_request( + "POST", + self.url, + access_token=self.admin_user_tok, + content={ + "user_id": self.other_user, + "content": {"msgtype": "m.text", "body": "test msg"}, + }, + ) + self.assertEqual(200, channel.code, msg=channel.json_body) + + # user has one invite + self._check_invite_and_join_status(self.other_user, 1, 0) + def test_server_notice_disabled(self) -> None: """Tests that server returns error if server notice is disabled""" channel = self.make_request( diff --git a/tests/rest/admin/test_user.py b/tests/rest/admin/test_user.py index 411e4ec005..1afd082707 100644 --- a/tests/rest/admin/test_user.py +++ b/tests/rest/admin/test_user.py @@ -1,4 +1,4 @@ -# Copyright 2018-2021 The Matrix.org Foundation C.I.C. +# Copyright 2018-2022 The Matrix.org Foundation C.I.C. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. @@ -904,6 +904,96 @@ class UsersListTestCase(unittest.HomeserverTestCase): ) +class UserDevicesTestCase(unittest.HomeserverTestCase): + """ + Tests user device management-related Admin APIs. + """ + + servlets = [ + synapse.rest.admin.register_servlets, + login.register_servlets, + sync.register_servlets, + ] + + def prepare( + self, reactor: MemoryReactor, clock: Clock, homeserver: HomeServer + ) -> None: + # Set up an Admin user to query the Admin API with. + self.admin_user_id = self.register_user("admin", "pass", admin=True) + self.admin_user_token = self.login("admin", "pass") + + # Set up a test user to query the devices of. + self.other_user_device_id = "TESTDEVICEID" + self.other_user_device_display_name = "My Test Device" + self.other_user_client_ip = "1.2.3.4" + self.other_user_user_agent = "EquestriaTechnology/123.0" + + self.other_user_id = self.register_user("user", "pass", displayname="User1") + self.other_user_token = self.login( + "user", + "pass", + device_id=self.other_user_device_id, + additional_request_fields={ + "initial_device_display_name": self.other_user_device_display_name, + }, + ) + + # Have the "other user" make a request so that the "last_seen_*" fields are + # populated in the tests below. + channel = self.make_request( + "GET", + "/_matrix/client/v3/sync", + access_token=self.other_user_token, + client_ip=self.other_user_client_ip, + custom_headers=[ + ("User-Agent", self.other_user_user_agent), + ], + ) + self.assertEqual(200, channel.code, msg=channel.json_body) + + def test_list_user_devices(self) -> None: + """ + Tests that a user's devices and attributes are listed correctly via the Admin API. + """ + # Request all devices of "other user" + channel = self.make_request( + "GET", + f"/_synapse/admin/v2/users/{self.other_user_id}/devices", + access_token=self.admin_user_token, + ) + self.assertEqual(200, channel.code, msg=channel.json_body) + + # Double-check we got the single device expected + user_devices = channel.json_body["devices"] + self.assertEqual(len(user_devices), 1) + self.assertEqual(channel.json_body["total"], 1) + + # Check that all the attributes of the device reported are as expected. + self._validate_attributes_of_device_response(user_devices[0]) + + # Request just a single device for "other user" by its ID + channel = self.make_request( + "GET", + f"/_synapse/admin/v2/users/{self.other_user_id}/devices/" + f"{self.other_user_device_id}", + access_token=self.admin_user_token, + ) + self.assertEqual(200, channel.code, msg=channel.json_body) + + # Check that all the attributes of the device reported are as expected. + self._validate_attributes_of_device_response(channel.json_body) + + def _validate_attributes_of_device_response(self, response: JsonDict) -> None: + # Check that all device expected attributes are present + self.assertEqual(response["user_id"], self.other_user_id) + self.assertEqual(response["device_id"], self.other_user_device_id) + self.assertEqual(response["display_name"], self.other_user_device_display_name) + self.assertEqual(response["last_seen_ip"], self.other_user_client_ip) + self.assertEqual(response["last_seen_user_agent"], self.other_user_user_agent) + self.assertIsInstance(response["last_seen_ts"], int) + self.assertGreater(response["last_seen_ts"], 0) + + class DeactivateAccountTestCase(unittest.HomeserverTestCase): servlets = [ diff --git a/tests/rest/client/test_account.py b/tests/rest/client/test_account.py index 7ae926dc9c..c1a7fb2f8a 100644 --- a/tests/rest/client/test_account.py +++ b/tests/rest/client/test_account.py @@ -488,7 +488,7 @@ class DeactivateTestCase(unittest.HomeserverTestCase): channel = self.make_request( "POST", "account/deactivate", request_data, access_token=tok ) - self.assertEqual(channel.code, 200) + self.assertEqual(channel.code, 200, channel.json_body) class WhoamiTestCase(unittest.HomeserverTestCase): @@ -641,21 +641,21 @@ class ThreepidEmailRestTestCase(unittest.HomeserverTestCase): def test_add_email_no_at(self) -> None: self._request_token_invalid_email( "address-without-at.bar", - expected_errcode=Codes.UNKNOWN, + expected_errcode=Codes.BAD_JSON, expected_error="Unable to parse email address", ) def test_add_email_two_at(self) -> None: self._request_token_invalid_email( "foo@foo@test.bar", - expected_errcode=Codes.UNKNOWN, + expected_errcode=Codes.BAD_JSON, expected_error="Unable to parse email address", ) def test_add_email_bad_format(self) -> None: self._request_token_invalid_email( "user@bad.example.net@good.example.com", - expected_errcode=Codes.UNKNOWN, + expected_errcode=Codes.BAD_JSON, expected_error="Unable to parse email address", ) @@ -1001,7 +1001,7 @@ class ThreepidEmailRestTestCase(unittest.HomeserverTestCase): HTTPStatus.BAD_REQUEST, channel.code, msg=channel.result["body"] ) self.assertEqual(expected_errcode, channel.json_body["errcode"]) - self.assertEqual(expected_error, channel.json_body["error"]) + self.assertIn(expected_error, channel.json_body["error"]) def _validate_token(self, link: str) -> None: # Remove the host diff --git a/tests/rest/client/test_models.py b/tests/rest/client/test_models.py new file mode 100644 index 0000000000..a9da00665e --- /dev/null +++ b/tests/rest/client/test_models.py @@ -0,0 +1,53 @@ +# Copyright 2022 The Matrix.org Foundation C.I.C. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +import unittest + +from pydantic import ValidationError + +from synapse.rest.client.models import EmailRequestTokenBody + + +class EmailRequestTokenBodyTestCase(unittest.TestCase): + base_request = { + "client_secret": "hunter2", + "email": "alice@wonderland.com", + "send_attempt": 1, + } + + def test_token_required_if_id_server_provided(self) -> None: + with self.assertRaises(ValidationError): + EmailRequestTokenBody.parse_obj( + { + **self.base_request, + "id_server": "identity.wonderland.com", + } + ) + with self.assertRaises(ValidationError): + EmailRequestTokenBody.parse_obj( + { + **self.base_request, + "id_server": "identity.wonderland.com", + "id_access_token": None, + } + ) + + def test_token_typechecked_when_id_server_provided(self) -> None: + with self.assertRaises(ValidationError): + EmailRequestTokenBody.parse_obj( + { + **self.base_request, + "id_server": "identity.wonderland.com", + "id_access_token": 1337, + } + ) diff --git a/tests/rest/client/test_register.py b/tests/rest/client/test_register.py index ab4277dd31..b781875d52 100644 --- a/tests/rest/client/test_register.py +++ b/tests/rest/client/test_register.py @@ -586,9 +586,9 @@ class RegisterRestServletTestCase(unittest.HomeserverTestCase): "require_at_registration": True, }, "account_threepid_delegates": { - "email": "https://id_server", "msisdn": "https://id_server", }, + "email": {"notif_from": "Synapse <synapse@example.com>"}, } ) def test_advertised_flows_captcha_and_terms_and_3pids(self) -> None: diff --git a/tests/rest/client/test_relations.py b/tests/rest/client/test_relations.py index d589f07314..651f4f415d 100644 --- a/tests/rest/client/test_relations.py +++ b/tests/rest/client/test_relations.py @@ -999,7 +999,7 @@ class BundledAggregationsTestCase(BaseRelationsTestCase): bundled_aggregations, ) - self._test_bundled_aggregations(RelationTypes.ANNOTATION, assert_annotations, 6) + self._test_bundled_aggregations(RelationTypes.ANNOTATION, assert_annotations, 7) def test_annotation_to_annotation(self) -> None: """Any relation to an annotation should be ignored.""" @@ -1035,7 +1035,7 @@ class BundledAggregationsTestCase(BaseRelationsTestCase): bundled_aggregations, ) - self._test_bundled_aggregations(RelationTypes.REFERENCE, assert_annotations, 6) + self._test_bundled_aggregations(RelationTypes.REFERENCE, assert_annotations, 7) def test_thread(self) -> None: """ @@ -1080,21 +1080,21 @@ class BundledAggregationsTestCase(BaseRelationsTestCase): # The "user" sent the root event and is making queries for the bundled # aggregations: they have participated. - self._test_bundled_aggregations(RelationTypes.THREAD, _gen_assert(True), 8) + self._test_bundled_aggregations(RelationTypes.THREAD, _gen_assert(True), 9) # The "user2" sent replies in the thread and is making queries for the # bundled aggregations: they have participated. # # Note that this re-uses some cached values, so the total number of # queries is much smaller. self._test_bundled_aggregations( - RelationTypes.THREAD, _gen_assert(True), 2, access_token=self.user2_token + RelationTypes.THREAD, _gen_assert(True), 3, access_token=self.user2_token ) # A user with no interactions with the thread: they have not participated. user3_id, user3_token = self._create_user("charlie") self.helper.join(self.room, user=user3_id, tok=user3_token) self._test_bundled_aggregations( - RelationTypes.THREAD, _gen_assert(False), 2, access_token=user3_token + RelationTypes.THREAD, _gen_assert(False), 3, access_token=user3_token ) def test_thread_with_bundled_aggregations_for_latest(self) -> None: @@ -1142,7 +1142,7 @@ class BundledAggregationsTestCase(BaseRelationsTestCase): bundled_aggregations["latest_event"].get("unsigned"), ) - self._test_bundled_aggregations(RelationTypes.THREAD, assert_thread, 8) + self._test_bundled_aggregations(RelationTypes.THREAD, assert_thread, 9) def test_nested_thread(self) -> None: """ diff --git a/tests/rest/client/test_retention.py b/tests/rest/client/test_retention.py index ac9c113354..9c8c1889d3 100644 --- a/tests/rest/client/test_retention.py +++ b/tests/rest/client/test_retention.py @@ -20,7 +20,7 @@ from synapse.api.constants import EventTypes from synapse.rest import admin from synapse.rest.client import login, room from synapse.server import HomeServer -from synapse.types import JsonDict +from synapse.types import JsonDict, create_requester from synapse.util import Clock from synapse.visibility import filter_events_for_client @@ -188,7 +188,7 @@ class RetentionTestCase(unittest.HomeserverTestCase): message_handler = self.hs.get_message_handler() create_event = self.get_success( message_handler.get_room_data( - self.user_id, room_id, EventTypes.Create, state_key="" + create_requester(self.user_id), room_id, EventTypes.Create, state_key="" ) ) diff --git a/tests/rest/client/test_shadow_banned.py b/tests/rest/client/test_shadow_banned.py index d9bd8c4a28..c50f034b34 100644 --- a/tests/rest/client/test_shadow_banned.py +++ b/tests/rest/client/test_shadow_banned.py @@ -26,7 +26,7 @@ from synapse.rest.client import ( room_upgrade_rest_servlet, ) from synapse.server import HomeServer -from synapse.types import UserID +from synapse.types import UserID, create_requester from synapse.util import Clock from tests import unittest @@ -275,7 +275,7 @@ class ProfileTestCase(_ShadowBannedBase): message_handler = self.hs.get_message_handler() event = self.get_success( message_handler.get_room_data( - self.banned_user_id, + create_requester(self.banned_user_id), room_id, "m.room.member", self.banned_user_id, @@ -310,7 +310,7 @@ class ProfileTestCase(_ShadowBannedBase): message_handler = self.hs.get_message_handler() event = self.get_success( message_handler.get_room_data( - self.banned_user_id, + create_requester(self.banned_user_id), room_id, "m.room.member", self.banned_user_id, diff --git a/tests/server.py b/tests/server.py index 9689e6a0cd..c447d5e4c4 100644 --- a/tests/server.py +++ b/tests/server.py @@ -61,6 +61,10 @@ from twisted.web.resource import IResource from twisted.web.server import Request, Site from synapse.config.database import DatabaseConnectionConfig +from synapse.events.presence_router import load_legacy_presence_router +from synapse.events.spamcheck import load_legacy_spam_checkers +from synapse.events.third_party_rules import load_legacy_third_party_event_rules +from synapse.handlers.auth import load_legacy_password_auth_providers from synapse.http.site import SynapseRequest from synapse.logging.context import ContextResourceUsage from synapse.server import HomeServer @@ -913,4 +917,14 @@ def setup_test_homeserver( # Make the threadpool and database transactions synchronous for testing. _make_test_homeserver_synchronous(hs) + # Load any configured modules into the homeserver + module_api = hs.get_module_api() + for module, config in hs.config.modules.loaded_modules: + module(config=config, api=module_api) + + load_legacy_spam_checkers(hs) + load_legacy_third_party_event_rules(hs) + load_legacy_presence_router(hs) + load_legacy_password_auth_providers(hs) + return hs diff --git a/tests/server_notices/test_resource_limits_server_notices.py b/tests/server_notices/test_resource_limits_server_notices.py index e07ae78fc4..bf403045e9 100644 --- a/tests/server_notices/test_resource_limits_server_notices.py +++ b/tests/server_notices/test_resource_limits_server_notices.py @@ -11,16 +11,19 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. - from unittest.mock import Mock +from twisted.test.proto_helpers import MemoryReactor + from synapse.api.constants import EventTypes, LimitBlockingTypes, ServerNoticeMsgType from synapse.api.errors import ResourceLimitError from synapse.rest import admin from synapse.rest.client import login, room, sync +from synapse.server import HomeServer from synapse.server_notices.resource_limits_server_notices import ( ResourceLimitsServerNotices, ) +from synapse.util import Clock from tests import unittest from tests.test_utils import make_awaitable @@ -52,7 +55,7 @@ class TestResourceLimitsServerNotices(unittest.HomeserverTestCase): return config - def prepare(self, reactor, clock, hs): + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: self.server_notices_sender = self.hs.get_server_notices_sender() # relying on [1] is far from ideal, but the only case where @@ -251,7 +254,7 @@ class TestResourceLimitsServerNoticesWithRealRooms(unittest.HomeserverTestCase): c["admin_contact"] = "mailto:user@test.com" return c - def prepare(self, reactor, clock, hs): + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: self.store = self.hs.get_datastores().main self.server_notices_sender = self.hs.get_server_notices_sender() self.server_notices_manager = self.hs.get_server_notices_manager() diff --git a/tests/storage/test_roommember.py b/tests/storage/test_roommember.py index 240b02cb9f..ceec690285 100644 --- a/tests/storage/test_roommember.py +++ b/tests/storage/test_roommember.py @@ -23,6 +23,7 @@ from synapse.util import Clock from tests import unittest from tests.server import TestHomeServer +from tests.test_utils import event_injection class RoomMemberStoreTestCase(unittest.HomeserverTestCase): @@ -157,6 +158,75 @@ class RoomMemberStoreTestCase(unittest.HomeserverTestCase): # Check that alice's display name is now None self.assertEqual(row[0]["display_name"], None) + def test_room_is_locally_forgotten(self): + """Test that when the last local user has forgotten a room it is known as forgotten.""" + # join two local and one remote user + self.room = self.helper.create_room_as(self.u_alice, tok=self.t_alice) + self.get_success( + event_injection.inject_member_event(self.hs, self.room, self.u_bob, "join") + ) + self.get_success( + event_injection.inject_member_event( + self.hs, self.room, self.u_charlie.to_string(), "join" + ) + ) + self.assertFalse( + self.get_success(self.store.is_locally_forgotten_room(self.room)) + ) + + # local users leave the room and the room is not forgotten + self.get_success( + event_injection.inject_member_event( + self.hs, self.room, self.u_alice, "leave" + ) + ) + self.get_success( + event_injection.inject_member_event(self.hs, self.room, self.u_bob, "leave") + ) + self.assertFalse( + self.get_success(self.store.is_locally_forgotten_room(self.room)) + ) + + # first user forgets the room, room is not forgotten + self.get_success(self.store.forget(self.u_alice, self.room)) + self.assertFalse( + self.get_success(self.store.is_locally_forgotten_room(self.room)) + ) + + # second (last local) user forgets the room and the room is forgotten + self.get_success(self.store.forget(self.u_bob, self.room)) + self.assertTrue( + self.get_success(self.store.is_locally_forgotten_room(self.room)) + ) + + def test_join_locally_forgotten_room(self): + """Tests if a user joins a forgotten room the room is not forgotten anymore.""" + self.room = self.helper.create_room_as(self.u_alice, tok=self.t_alice) + self.assertFalse( + self.get_success(self.store.is_locally_forgotten_room(self.room)) + ) + + # after leaving and forget the room, it is forgotten + self.get_success( + event_injection.inject_member_event( + self.hs, self.room, self.u_alice, "leave" + ) + ) + self.get_success(self.store.forget(self.u_alice, self.room)) + self.assertTrue( + self.get_success(self.store.is_locally_forgotten_room(self.room)) + ) + + # after rejoin the room is not forgotten anymore + self.get_success( + event_injection.inject_member_event( + self.hs, self.room, self.u_alice, "join" + ) + ) + self.assertFalse( + self.get_success(self.store.is_locally_forgotten_room(self.room)) + ) + class CurrentStateMembershipUpdateTestCase(unittest.HomeserverTestCase): def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: diff --git a/tests/test_metrics.py b/tests/test_metrics.py index b4574b2ffe..1a70eddc9b 100644 --- a/tests/test_metrics.py +++ b/tests/test_metrics.py @@ -12,7 +12,16 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. +try: + from importlib import metadata +except ImportError: + import importlib_metadata as metadata # type: ignore[no-redef] +from unittest.mock import patch + +from pkg_resources import parse_version + +from synapse.app._base import _set_prometheus_client_use_created_metrics from synapse.metrics import REGISTRY, InFlightGauge, generate_latest from synapse.util.caches.deferred_cache import DeferredCache @@ -162,3 +171,30 @@ class CacheMetricsTests(unittest.HomeserverTestCase): self.assertEqual(items["synapse_util_caches_cache_size"], "1.0") self.assertEqual(items["synapse_util_caches_cache_max_size"], "777.0") + + +class PrometheusMetricsHackTestCase(unittest.HomeserverTestCase): + if parse_version(metadata.version("prometheus_client")) < parse_version("0.14.0"): + skip = "prometheus-client too old" + + def test_created_metrics_disabled(self) -> None: + """ + Tests that a brittle hack, to disable `_created` metrics, works. + This involves poking at the internals of prometheus-client. + It's not the end of the world if this doesn't work. + + This test gives us a way to notice if prometheus-client changes + their internals. + """ + import prometheus_client.metrics + + PRIVATE_FLAG_NAME = "_use_created" + + # By default, the pesky `_created` metrics are enabled. + # Check this assumption is still valid. + self.assertTrue(getattr(prometheus_client.metrics, PRIVATE_FLAG_NAME)) + + with patch("prometheus_client.metrics") as mock: + setattr(mock, PRIVATE_FLAG_NAME, True) + _set_prometheus_client_use_created_metrics(False) + self.assertFalse(getattr(mock, PRIVATE_FLAG_NAME, False)) diff --git a/tests/unittest.py b/tests/unittest.py index bec4a3d023..975b0a23a7 100644 --- a/tests/unittest.py +++ b/tests/unittest.py @@ -677,14 +677,29 @@ class HomeserverTestCase(TestCase): username: str, password: str, device_id: Optional[str] = None, + additional_request_fields: Optional[Dict[str, str]] = None, custom_headers: Optional[Iterable[CustomHeaderType]] = None, ) -> str: """ Log in a user, and get an access token. Requires the Login API be registered. + + Args: + username: The localpart to assign to the new user. + password: The password to assign to the new user. + device_id: An optional device ID to assign to the new device created during + login. + additional_request_fields: A dictionary containing any additional /login + request fields and their values. + custom_headers: Custom HTTP headers and values to add to the /login request. + + Returns: + The newly registered user's Matrix ID. """ body = {"type": "m.login.password", "user": username, "password": password} if device_id: body["device_id"] = device_id + if additional_request_fields: + body.update(additional_request_fields) channel = self.make_request( "POST", |