From a9481223d1d5a8b3bf0d7ce2140dd3c919481f4f Mon Sep 17 00:00:00 2001 From: Marcus Date: Tue, 30 Nov 2021 12:49:20 +0100 Subject: Improved push typing (#11409) Co-authored-by: Sean Quah <8349537+squahtx@users.noreply.github.com> --- docs/templates.md | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'docs') diff --git a/docs/templates.md b/docs/templates.md index a240f58b54..2b66e9d862 100644 --- a/docs/templates.md +++ b/docs/templates.md @@ -71,7 +71,12 @@ Below are the templates Synapse will look for when generating the content of an * `sender_avatar_url`: the avatar URL (as a `mxc://` URL) for the event's sender * `sender_hash`: a hash of the user ID of the sender + * `msgtype`: the type of the message + * `body_text_html`: html representation of the message + * `body_text_plain`: plaintext representation of the message + * `image_url`: mxc url of an image, when "msgtype" is "m.image" * `link`: a `matrix.to` link to the room + * `avator_url`: url to the room's avator * `reason`: information on the event that triggered the email to be sent. It's an object with the following attributes: * `room_id`: the ID of the room the event was sent in -- cgit 1.5.1 From f1795463bf503a6fca909d77f598f641f9349f56 Mon Sep 17 00:00:00 2001 From: Shay Date: Tue, 30 Nov 2021 19:05:20 -0800 Subject: Add a note about huge pages to our Postgres doc (#11467) * Add note to postgres doc about hugepages * Newsfragment --- changelog.d/11467.misc | 1 + docs/postgres.md | 3 +++ 2 files changed, 4 insertions(+) create mode 100644 changelog.d/11467.misc (limited to 'docs') diff --git a/changelog.d/11467.misc b/changelog.d/11467.misc new file mode 100644 index 0000000000..84e8a5ab4e --- /dev/null +++ b/changelog.d/11467.misc @@ -0,0 +1 @@ +Add a note about postgres memory management and hugepages to postgres doc. \ No newline at end of file diff --git a/docs/postgres.md b/docs/postgres.md index 083b0aaff0..e4861c1f12 100644 --- a/docs/postgres.md +++ b/docs/postgres.md @@ -118,6 +118,9 @@ performance: Note that the appropriate values for those fields depend on the amount of free memory the database host has available. +Additionally, admins of large deployments might want to consider using huge pages +to help manage memory, especially when using large values of `shared_buffers`. You +can read more about that [here](https://www.postgresql.org/docs/10/kernel-resources.html#LINUX-HUGE-PAGES). ## Porting from SQLite -- cgit 1.5.1 From b0eb64ff7bf6bde42046e091f8bdea9b7aab5f04 Mon Sep 17 00:00:00 2001 From: Etienne Dysli Metref Date: Wed, 1 Dec 2021 10:40:51 +0100 Subject: Remove mention of OIDC certification from Dex (#11470) Dex isn't yet [1,2] a certified OpenID Provider implementation. As of today, it's not on the list maintained by the OpenID Foundation. [3] [1] https://github.com/dexidp/dex/issues/42 [2] https://github.com/dexidp/dex/issues/262 [3] https://openid.net/certification/ --- docs/openid.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'docs') diff --git a/docs/openid.md b/docs/openid.md index c74e8bda60..f366709c69 100644 --- a/docs/openid.md +++ b/docs/openid.md @@ -83,7 +83,7 @@ oidc_providers: ### Dex -[Dex][dex-idp] is a simple, open-source, certified OpenID Connect Provider. +[Dex][dex-idp] is a simple, open-source OpenID Connect Provider. Although it is designed to help building a full-blown provider with an external database, it can be configured with static passwords in a config file. -- cgit 1.5.1 From b9fef1a7cdfcc128fa589a32160e6aa7ed8964d7 Mon Sep 17 00:00:00 2001 From: Richard van der Hoff <1389908+richvdh@users.noreply.github.com> Date: Wed, 1 Dec 2021 10:57:55 +0000 Subject: Update openid.md fix header level --- docs/openid.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'docs') diff --git a/docs/openid.md b/docs/openid.md index f366709c69..ff9de9d5b8 100644 --- a/docs/openid.md +++ b/docs/openid.md @@ -523,7 +523,7 @@ The synapse config will look like this: email_template: "{{ user.email }}" ``` -## Django OAuth Toolkit +### Django OAuth Toolkit [django-oauth-toolkit](https://github.com/jazzband/django-oauth-toolkit) is a Django application providing out of the box all the endpoints, data and logic -- cgit 1.5.1 From 153194c7717d8016b0eb974c81b1baee7dc1917d Mon Sep 17 00:00:00 2001 From: Brendan Abolivier Date: Wed, 1 Dec 2021 15:13:01 +0100 Subject: Link background update controller docs to summary (#11475) --- changelog.d/11475.feature | 1 + docs/SUMMARY.md | 1 + 2 files changed, 2 insertions(+) create mode 100644 changelog.d/11475.feature (limited to 'docs') diff --git a/changelog.d/11475.feature b/changelog.d/11475.feature new file mode 100644 index 0000000000..aba3292015 --- /dev/null +++ b/changelog.d/11475.feature @@ -0,0 +1 @@ +Add plugin support for controlling database background updates. diff --git a/docs/SUMMARY.md b/docs/SUMMARY.md index cdedf8bccc..900254ff64 100644 --- a/docs/SUMMARY.md +++ b/docs/SUMMARY.md @@ -44,6 +44,7 @@ - [Presence router callbacks](modules/presence_router_callbacks.md) - [Account validity callbacks](modules/account_validity_callbacks.md) - [Password auth provider callbacks](modules/password_auth_provider_callbacks.md) + - [Background update controller callbacks](modules/background_update_controller_callbacks.md) - [Porting a legacy module to the new interface](modules/porting_legacy_module.md) - [Workers](workers.md) - [Using `synctl` with Workers](synctl_workers.md) -- cgit 1.5.1 From 84dc50e160a2ec6590813374b5a1e58b97f7a18d Mon Sep 17 00:00:00 2001 From: Shay Date: Wed, 1 Dec 2021 10:12:19 -0800 Subject: Port wiki pages to documentation website (#11402) * move wiki pages to synapse/docs and add a few titles where necessary * update SUMMARY.md with added pages * add changelog * move incorrectly located newsfragment * update changelog number * snake case added files and update summary.md accordingly * update issue/pr links * update relative links to docs * update changelog to indicate that we moved wiki pages to the docs and state reasoning * revert unintentional change to CHANGES.md * add link Co-authored-by: Andrew Morgan <1342360+anoadragon453@users.noreply.github.com> * Update CHANGES.md Co-authored-by: Andrew Morgan <1342360+anoadragon453@users.noreply.github.com> Co-authored-by: Andrew Morgan <1342360+anoadragon453@users.noreply.github.com> --- CHANGES.md | 17 +++ changelog.d/11402.misc | 1 + docs/SUMMARY.md | 6 + .../running_synapse_on_single_board_computers.md | 74 ++++++++++ docs/usage/administration/admin_faq.md | 96 +++++++++++++ .../administration/database_maintenance_tools.md | 36 +++++ docs/usage/administration/state_groups.md | 25 ++++ ...understanding_synapse_through_grafana_graphs.md | 72 ++++++++++ docs/usage/administration/useful_sql_for_admins.md | 156 +++++++++++++++++++++ 9 files changed, 483 insertions(+) create mode 100644 changelog.d/11402.misc create mode 100644 docs/other/running_synapse_on_single_board_computers.md create mode 100644 docs/usage/administration/admin_faq.md create mode 100644 docs/usage/administration/database_maintenance_tools.md create mode 100644 docs/usage/administration/state_groups.md create mode 100644 docs/usage/administration/understanding_synapse_through_grafana_graphs.md create mode 100644 docs/usage/administration/useful_sql_for_admins.md (limited to 'docs') diff --git a/CHANGES.md b/CHANGES.md index c283e33876..2e3f0da961 100644 --- a/CHANGES.md +++ b/CHANGES.md @@ -1,3 +1,19 @@ +UNRELEASED +========== + +We've decided to move the existing, somewhat stagnant pages from the GitHub wiki +to the [documentation website](https://matrix-org.github.io/synapse/latest/). +This was done for two reasons. The first was to ensure that changes are checked by +multiple authors before being committed (everyone makes mistakes!) and the second +was visibility of the documentation. Not everyone knows that Synapse has some very +useful information hidden away in its GitHub wiki pages. Bringing them to the +documentation website should help with visibility, as well as keep all Synapse documentation +in one, easily-searchable location. + +Note that contributions to the documentation website happen through [GitHub pull +requests](https://github.com/matrix-org/synapse/pulls). Please visit [#synapse-dev:matrix.org](https://matrix.to/#/#synapse-dev:matrix.org) +if you need help with the process! + Synapse 1.48.0 (2021-11-30) =========================== @@ -86,6 +102,7 @@ Internal Changes - Refactor including the bundled relations when serializing an event. ([\#11408](https://github.com/matrix-org/synapse/issues/11408)) + Synapse 1.47.1 (2021-11-23) =========================== diff --git a/changelog.d/11402.misc b/changelog.d/11402.misc new file mode 100644 index 0000000000..c956338744 --- /dev/null +++ b/changelog.d/11402.misc @@ -0,0 +1 @@ +Add wiki pages to documentation website. \ No newline at end of file diff --git a/docs/SUMMARY.md b/docs/SUMMARY.md index 900254ff64..41c8f0fbc9 100644 --- a/docs/SUMMARY.md +++ b/docs/SUMMARY.md @@ -67,7 +67,12 @@ - [Server Version](admin_api/version_api.md) - [Manhole](manhole.md) - [Monitoring](metrics-howto.md) + - [Understanding Synapse Through Grafana Graphs](usage/administration/understanding_synapse_through_grafana_graphs.md) + - [Useful SQL for Admins](usage/administration/useful_sql_for_admins.md) + - [Database Maintenance Tools](usage/administration/database_maintenance_tools.md) + - [State Groups](usage/administration/state_groups.md) - [Request log format](usage/administration/request_log.md) + - [Admin FAQ](usage/administration/admin_faq.md) - [Scripts]() # Development @@ -95,3 +100,4 @@ # Other - [Dependency Deprecation Policy](deprecation_policy.md) + - [Running Synapse on a Single-Board Computer](other/running_synapse_on_single_board_computers.md) diff --git a/docs/other/running_synapse_on_single_board_computers.md b/docs/other/running_synapse_on_single_board_computers.md new file mode 100644 index 0000000000..ea14afa8b2 --- /dev/null +++ b/docs/other/running_synapse_on_single_board_computers.md @@ -0,0 +1,74 @@ +## Summary of performance impact of running on resource constrained devices such as SBCs + +I've been running my homeserver on a cubietruck at home now for some time and am often replying to statements like "you need loads of ram to join large rooms" with "it works fine for me". I thought it might be useful to curate a summary of the issues you're likely to run into to help as a scaling-down guide, maybe highlight these for development work or end up as documentation. It seems that once you get up to about 4x1.5GHz arm64 4GiB these issues are no longer a problem. + +- **Platform**: 2x1GHz armhf 2GiB ram [Single-board computers](https://wiki.debian.org/CheapServerBoxHardware), SSD, postgres. + +### Presence + +This is the main reason people have a poor matrix experience on resource constrained homeservers. Element web will frequently be saying the server is offline while the python process will be pegged at 100% cpu. This feature is used to tell when other users are active (have a client app in the foreground) and therefore more likely to respond, but requires a lot of network activity to maintain even when nobody is talking in a room. + +![Screenshot_2020-10-01_19-29-46](https://user-images.githubusercontent.com/71895/94848963-a47a3580-041c-11eb-8b6e-acb772b4259e.png) + +While synapse does have some performance issues with presence [#3971](https://github.com/matrix-org/synapse/issues/3971), the fundamental problem is that this is an easy feature to implement for a centralised service at nearly no overhead, but federation makes it combinatorial [#8055](https://github.com/matrix-org/synapse/issues/8055). There is also a client-side config option which disables the UI and idle tracking [enable_presence_by_hs_url] to blacklist the largest instances but I didn't notice much difference, so I recommend disabling the feature entirely at the server level as well. + +[enable_presence_by_hs_url]: https://github.com/vector-im/element-web/blob/v1.7.8/config.sample.json#L45 + +### Joining + +Joining a "large", federated room will initially fail with the below message in Element web, but waiting a while (10-60mins) and trying again will succeed without any issue. What counts as "large" is not message history, user count, connections to homeservers or even a simple count of the state events, it is instead how long the state resolution algorithm takes. However, each of those numbers are reasonable proxies, so we can use them as estimates since user count is one of the few things you see before joining. + +![Screenshot_2020-10-02_17-15-06](https://user-images.githubusercontent.com/71895/94945781-18771500-04d3-11eb-8419-83c2da73a341.png) + +This is [#1211](https://github.com/matrix-org/synapse/issues/1211) and will also hopefully be mitigated by peeking [matrix-org/matrix-doc#2753](https://github.com/matrix-org/matrix-doc/pull/2753) so at least you don't need to wait for a join to complete before finding out if it's the kind of room you want. Note that you should first disable presence, otherwise it'll just make the situation worse [#3120](https://github.com/matrix-org/synapse/issues/3120). There is a lot of database interaction too, so make sure you've [migrated your data](../postgres.md) from the default sqlite to postgresql. Personally, I recommend patience - once the initial join is complete there's rarely any issues with actually interacting with the room, but if you like you can just block "large" rooms entirely. + +### Sessions + +Anything that requires modifying the device list [#7721](https://github.com/matrix-org/synapse/issues/7721) will take a while to propagate, again taking the client "Offline" until it's complete. This includes signing in and out, editing the public name and verifying e2ee. The main mitigation I recommend is to keep long-running sessions open e.g. by using Firefox SSB "Use this site in App mode" or Chromium PWA "Install Element". + +### Recommended configuration + +Put the below in a new file at /etc/matrix-synapse/conf.d/sbc.yaml to override the defaults in homeserver.yaml. + +``` +# Set to false to disable presence tracking on this homeserver. +use_presence: false + +# When this is enabled, the room "complexity" will be checked before a user +# joins a new remote room. If it is above the complexity limit, the server will +# disallow joining, or will instantly leave. +limit_remote_rooms: + # Uncomment to enable room complexity checking. + #enabled: true + complexity: 3.0 + +# Database configuration +database: + name: psycopg2 + args: + user: matrix-synapse + # Generate a long, secure one with a password manager + password: hunter2 + database: matrix-synapse + host: localhost + cp_min: 5 + cp_max: 10 +``` + +Currently the complexity is measured by [current_state_events / 500](https://github.com/matrix-org/synapse/blob/v1.20.1/synapse/storage/databases/main/events_worker.py#L986). You can find join times and your most complex rooms like this: + +``` +admin@homeserver:~$ zgrep '/client/r0/join/' /var/log/matrix-synapse/homeserver.log* | awk '{print $18, $25}' | sort --human-numeric-sort +29.922sec/-0.002sec /_matrix/client/r0/join/%23debian-fasttrack%3Apoddery.com +182.088sec/0.003sec /_matrix/client/r0/join/%23decentralizedweb-general%3Amatrix.org +911.625sec/-570.847sec /_matrix/client/r0/join/%23synapse%3Amatrix.org + +admin@homeserver:~$ sudo --user postgres psql matrix-synapse --command 'select canonical_alias, joined_members, current_state_events from room_stats_state natural join room_stats_current where canonical_alias is not null order by current_state_events desc fetch first 5 rows only' + canonical_alias | joined_members | current_state_events +-------------------------------+----------------+---------------------- + #_oftc_#debian:matrix.org | 871 | 52355 + #matrix:matrix.org | 6379 | 10684 + #irc:matrix.org | 461 | 3751 + #decentralizedweb-general:matrix.org | 997 | 1509 + #whatsapp:maunium.net | 554 | 854 +``` \ No newline at end of file diff --git a/docs/usage/administration/admin_faq.md b/docs/usage/administration/admin_faq.md new file mode 100644 index 0000000000..162af0c741 --- /dev/null +++ b/docs/usage/administration/admin_faq.md @@ -0,0 +1,96 @@ +## Admin FAQ + +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 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. + + UPDATE users SET admin = 1 WHERE name = '@foo:bar.com'; + +What servers are my server talking to? +--- +Run this sql query on your db: + + SELECT * FROM destinations; + +What servers are currently participating in this room? +--- +Run this sql query on your db: + + SELECT DISTINCT split_part(state_key, ':', 2) + FROM current_state_events AS c + INNER JOIN room_memberships AS m USING (room_id, event_id) + WHERE room_id = '!cURbafjkfsMDVwdRDQ:matrix.org' AND membership = 'join'; + +What users are registered on my server? +--- + + SELECT NAME from users; + +Manually resetting passwords: +--- +See https://github.com/matrix-org/synapse/blob/master/README.rst#password-reset + +I have a problem with my server. Can I just delete my database and start again? +--- +Deleting your database is unlikely to make anything better. + +It's easy to make the mistake of thinking that you can start again from a clean slate by dropping your database, but things don't work like that in a federated network: lots of other servers have information about your server. + +For example: other servers might think that you are in a room, your server will think that you are not, and you'll probably be unable to interact with that room in a sensible way ever again. + +In general, there are better solutions to any problem than dropping the database. Come and seek help in https://matrix.to/#/#synapse:matrix.org. + +There are two exceptions when it might be sensible to delete your database and start again: +* You have *never* joined any rooms which are federated with other servers. For instance, a local deployment which the outside world can't talk to. +* You are changing the `server_name` in the homeserver configuration. In effect this makes your server a completely new one from the point of view of the network, so in this case it makes sense to start with a clean database. +(In both cases you probably also want to clear out the media_store.) + +I've stuffed up access to my room, how can I delete it to free up the alias? +--- +Using the following curl command: + + curl -H 'Authorization: Bearer ' -X DELETE https://matrix.org/_matrix/client/r0/directory/room/ + +\ - can be obtained in riot by looking in the riot settings, down the bottom is: +Access Token:\ + +\ - the room alias, eg. #my_room:matrix.org this possibly needs to be URL encoded also, for example %23my_room%3Amatrix.org + +How can I find the lines corresponding to a given HTTP request in my homeserver log? +--- + +Synapse tags each log line according to the HTTP request it is processing. When it finishes processing each request, it logs a line containing the words `Processed request: `. For example: + +``` +2019-02-14 22:35:08,196 - synapse.access.http.8008 - 302 - INFO - GET-37 - ::1 - 8008 - {@richvdh:localhost} Processed request: 0.173sec/0.001sec (0.002sec, 0.000sec) (0.027sec/0.026sec/2) 687B 200 "GET /_matrix/client/r0/sync HTTP/1.1" "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36" [0 dbevts]" +``` + +Here we can see that the request has been tagged with `GET-37`. (The tag depends on the method of the HTTP request, so might start with `GET-`, `PUT-`, `POST-`, `OPTIONS-` or `DELETE-`.) So to find all lines corresponding to this request, we can do: + +``` +grep 'GET-37' homeserver.log +``` + +If you want to paste that output into a github issue or matrix room, please remember to surround it with triple-backticks (```) to make it legible (see https://help.github.com/en/articles/basic-writing-and-formatting-syntax#quoting-code). + + +What do all those fields in the 'Processed' line mean? +--- +See [Request log format](request_log.md). + + +What are the biggest rooms on my server? +--- + +```sql +SELECT s.canonical_alias, g.room_id, count(*) AS num_rows +FROM + state_groups_state AS g, + room_stats_state AS s +WHERE g.room_id = s.room_id +GROUP BY s.canonical_alias, g.room_id +ORDER BY num_rows desc +LIMIT 10; +``` \ No newline at end of file diff --git a/docs/usage/administration/database_maintenance_tools.md b/docs/usage/administration/database_maintenance_tools.md new file mode 100644 index 0000000000..2c29ccfe69 --- /dev/null +++ b/docs/usage/administration/database_maintenance_tools.md @@ -0,0 +1,36 @@ +This blog post by Victor Berger explains how to use many of the tools listed on this page: https://levans.fr/shrink-synapse-database.html + +# List of useful tools and scripts for maintenance Synapse database: + +## [Purge Remote Media API](../../admin_api/media_admin_api.md#purge-remote-media-api) +The purge remote media API allows server admins to purge old cached remote media. + +#### Purge local media + +There is no purge API for local media because you may be the only one with a copy. If you are sure you want to delete local media you could use something like the following to delete media that hasn't been accessed in a while. + +``` +find /path/to/synapse/media_store/local_content -atime +365 -delete +find /path/to/synapse/media_store/local_thumbnails -atime +365 -delete +``` + +This will delete media that hasn't been accessed in 365 days. + +**Warning, check noatime flag**: You also have to double-check that the filesystem where synapse's media store don't have [noatime flag](https://unix.stackexchange.com/questions/219015/how-to-disable-access-time-settings-in-debian-linux/219017#219017). Check it with `mount`, `noatime` is something that is usually enabled by default to reduce read-write operations in the filesystem for a feature is not so demanded. + +## [Purge History API](../../admin_api/purge_history_api.md) +The purge history API allows server admins to purge historic events from their database, reclaiming disk space. + +## [synapse_janitor.sql](https://github.com/xwiki-labs/synapse_scripts) + +- this project is [unmantained and dangerous](https://github.com/xwiki-labs/synapse_scripts#unmaintained-and-dangerous) +- USE WITH CAUTION. It may cause database corruption (see https://github.com/matrix-org/synapse/issues/7305 for example). +- ["Our team hasn't used any of these scripts for some time (possibly years) (...) if anyone wants to volunteer to maintain this repo I'd be happy to transfer ownership.](https://github.com/xwiki-labs/synapse_scripts/pull/12#issuecomment-617275345) + +Cleans a synapse Postgres database of deleted messages and abandoned rooms. + +## [synapse-compress-state](https://github.com/matrix-org/rust-synapse-compress-state) +Tool for compressing (deduplicating) `state_groups_state` table. + +## [SQL for analyzing Synapse PostgreSQL database stats](https://github.com/matrix-org/synapse/wiki/SQL-for-analyzing-Synapse-PostgreSQL-database-stats) +Some easy SQL that reports useful stat about Matrix Synapse database. \ No newline at end of file diff --git a/docs/usage/administration/state_groups.md b/docs/usage/administration/state_groups.md new file mode 100644 index 0000000000..f1dee7accf --- /dev/null +++ b/docs/usage/administration/state_groups.md @@ -0,0 +1,25 @@ +# How do State Groups work? + +As a general rule, I encourage people who want to understand the deepest darkest secrets of the database schema to drop by #synapse-dev:matrix.org and ask questions. + +However, one question that comes up frequently is that of how "state groups" work, and why the `state_groups_state` table gets so big, so here's an attempt to answer that question. + +We need to be able to relatively quickly calculate the state of a room at any point in that room's history. In other words, we need to know the state of the room at each event in that room. This is done as follows: + +A sequence of events where the state is the same are grouped together into a `state_group`; the mapping is recorded in `event_to_state_groups`. (Technically speaking, since a state event usually changes the state in the room, we are recording the state of the room *after* the given event id: which is to say, to a handwavey simplification, the first event in a state group is normally a state event, and others in the same state group are normally non-state-events.) + +`state_groups` records, for each state group, the id of the room that we're looking at, and also the id of the first event in that group. (I'm not sure if that event id is used much in practice.) + +Now, if we stored all the room state for each `state_group`, that would be a huge amount of data. Instead, for each state group, we normally store the difference between the state in that group and some other state group, and only occasionally (every 100 state changes or so) record the full state. + +So, most state groups have an entry in `state_group_edges` (don't ask me why it's not a column in `state_groups`) which records the previous state group in the room, and `state_groups_state` records the differences in state since that previous state group. + +A full state group just records the event id for each piece of state in the room at that point. + +## Known bugs with state groups + +There are various reasons that we can end up creating many more state groups than we need: see https://github.com/matrix-org/synapse/issues/3364 for more details. + +## Compression tool + +There is a tool at https://github.com/matrix-org/rust-synapse-compress-state which can compress the `state_groups_state` on a room by-room basis (essentially, it reduces the number of "full" state groups). This can result in dramatic reductions of the storage used. \ No newline at end of file diff --git a/docs/usage/administration/understanding_synapse_through_grafana_graphs.md b/docs/usage/administration/understanding_synapse_through_grafana_graphs.md new file mode 100644 index 0000000000..bfe4360b4e --- /dev/null +++ b/docs/usage/administration/understanding_synapse_through_grafana_graphs.md @@ -0,0 +1,72 @@ +## Understanding Synapse through Grafana graphs + +It is possible monitor much of the internal state of Synapse using [Prometheus](https://prometheus.io) metrics and [Grafana](https://grafana.com/). A guide for configuring Synapse to provide metrics is available [here](../../metrics-howto.md) and information on setting up Grafana is [here](https://github.com/matrix-org/synapse/tree/master/contrib/grafana). In this setup, Prometheus will periodically scrape the information Synapse provides and store a record of it over time. Grafana is then used as an interface to query and present this information through a series of pretty graphs. + +Once you have grafana set up, and assuming you're using [our grafana dashboard template](https://github.com/matrix-org/synapse/blob/master/contrib/grafana/synapse.json), look for the following graphs when debugging a slow/overloaded Synapse: + +## Message Event Send Time + +![image](https://user-images.githubusercontent.com/1342360/82239409-a1c8e900-9930-11ea-8081-e4614e0c63f4.png) + +This, along with the CPU and Memory graphs, is a good way to check the general health of your Synapse instance. It represents how long it takes for a user on your homeserver to send a message. + +## Transaction Count and Transaction Duration + +![image](https://user-images.githubusercontent.com/1342360/82239985-8d392080-9931-11ea-80d0-843ab2f22e1e.png) + +![image](https://user-images.githubusercontent.com/1342360/82240050-ab068580-9931-11ea-98f1-f94671cbac9a.png) + +These graphs show the database transactions that are occurring the most frequently, as well as those are that are taking the most amount of time to execute. + +![image](https://user-images.githubusercontent.com/1342360/82240192-e86b1300-9931-11ea-9aac-3e2c9bfa6fdc.png) + +In the first graph, we can see obvious spikes corresponding to lots of `get_user_by_id` transactions. This would be useful information to figure out which part of the Synapse codebase is potentially creating a heavy load on the system. However, be sure to cross-reference this with Transaction Duration, which states that `get_users_by_id` is actually a very quick database transaction and isn't causing as much load as others, like `persist_events`: + +![image](https://user-images.githubusercontent.com/1342360/82240467-62030100-9932-11ea-8db9-917f2d977fe1.png) + +Still, it's probably worth investigating why we're getting users from the database that often, and whether it's possible to reduce the amount of queries we make by adjusting our cache factor(s). + +The `persist_events` transaction is responsible for saving new room events to the Synapse database, so can often show a high transaction duration. + +## Federation + +The charts in the "Federation" section show information about incoming and outgoing federation requests. Federation data can be divided into two basic types: + +- PDU (Persistent Data Unit) - room events: messages, state events (join/leave), etc. These are permanently stored in the database. +- EDU (Ephemeral Data Unit) - other data, which need not be stored permanently, such as read receipts, typing notifications. + +The "Outgoing EDUs by type" chart shows the EDUs within outgoing federation requests by type: `m.device_list_update`, `m.direct_to_device`, `m.presence`, `m.receipt`, `m.typing`. + +If you see a large number of `m.presence` EDUs and are having trouble with too much CPU load, you can disable `presence` in the Synapse config. See also [#3971](https://github.com/matrix-org/synapse/issues/3971). + +## Caches + +![image](https://user-images.githubusercontent.com/1342360/82240572-8b239180-9932-11ea-96ff-6b5f0e57ebe5.png) + +![image](https://user-images.githubusercontent.com/1342360/82240666-b8703f80-9932-11ea-86af-9f663988d8da.png) + +This is quite a useful graph. It shows how many times Synapse attempts to retrieve a piece of data from a cache which the cache did not contain, thus resulting in a call to the database. We can see here that the `_get_joined_profile_from_event_id` cache is being requested a lot, and often the data we're after is not cached. + +Cross-referencing this with the Eviction Rate graph, which shows that entries are being evicted from `_get_joined_profile_from_event_id` quite often: + +![image](https://user-images.githubusercontent.com/1342360/82240766-de95df80-9932-11ea-8c15-5acfc57c48da.png) + +we should probably consider raising the size of that cache by raising its cache factor (a multiplier value for the size of an individual cache). Information on doing so is available [here](https://github.com/matrix-org/synapse/blob/ee421e524478c1ad8d43741c27379499c2f6135c/docs/sample_config.yaml#L608-L642) (note that the configuration of individual cache factors through the configuration file is available in Synapse v1.14.0+, whereas doing so through environment variables has been supported for a very long time). Note that this will increase Synapse's overall memory usage. + +## Forward Extremities + +![image](https://user-images.githubusercontent.com/1342360/82241440-13566680-9934-11ea-8b88-ba468db937ed.png) + +Forward extremities are the leaf events at the end of a DAG in a room, aka events that have no children. The more exist in a room, the more [state resolution](https://matrix.org/docs/spec/server_server/r0.1.3#room-state-resolution) that Synapse needs to perform (hint: it's an expensive operation). While Synapse has code to prevent too many of these existing at one time in a room, bugs can sometimes make them crop up again. + +If a room has >10 forward extremities, it's worth checking which room is the culprit and potentially removing them using the SQL queries mentioned in [#1760](https://github.com/matrix-org/synapse/issues/1760). + +## Garbage Collection + +![image](https://user-images.githubusercontent.com/1342360/82241911-da6ac180-9934-11ea-9a0d-a311fe22acd0.png) + +Large spikes in garbage collection times (bigger than shown here, I'm talking in the multiple seconds range), can cause lots of problems in Synapse performance. It's more an indicator of problems, and a symptom of other problems though, so check other graphs for what might be causing it. + +## Final Thoughts + +If you're still having performance problems with your Synapse instance and you've tried everything you can, it may just be a lack of system resources. Consider adding more CPU and RAM, and make use of [worker mode](../../workers.md) to make use of multiple CPU cores / multiple machines for your homeserver. \ No newline at end of file diff --git a/docs/usage/administration/useful_sql_for_admins.md b/docs/usage/administration/useful_sql_for_admins.md new file mode 100644 index 0000000000..d4aada3272 --- /dev/null +++ b/docs/usage/administration/useful_sql_for_admins.md @@ -0,0 +1,156 @@ +## Some useful SQL queries for Synapse Admins + +## Size of full matrix db +`SELECT pg_size_pretty( pg_database_size( 'matrix' ) );` +### Result example: +``` +pg_size_pretty +---------------- + 6420 MB +(1 row) +``` +## Show top 20 larger rooms by state events count +```sql +SELECT r.name, s.room_id, s.current_state_events + FROM room_stats_current s + LEFT JOIN room_stats_state r USING (room_id) + ORDER BY current_state_events DESC + LIMIT 20; +``` + +and by state_group_events count: +```sql +SELECT rss.name, s.room_id, count(s.room_id) FROM state_groups_state s +LEFT JOIN room_stats_state rss USING (room_id) +GROUP BY s.room_id, rss.name +ORDER BY count(s.room_id) DESC +LIMIT 20; +``` +plus same, but with join removed for performance reasons: +```sql +SELECT s.room_id, count(s.room_id) FROM state_groups_state s +GROUP BY s.room_id +ORDER BY count(s.room_id) DESC +LIMIT 20; +``` + +## Show top 20 larger tables by row count +```sql +SELECT relname, n_live_tup as rows + FROM pg_stat_user_tables + ORDER BY n_live_tup DESC + LIMIT 20; +``` +This query is quick, but may be very approximate, for exact number of rows use `SELECT COUNT(*) FROM `. +### Result example: +``` +state_groups_state - 161687170 +event_auth - 8584785 +event_edges - 6995633 +event_json - 6585916 +event_reference_hashes - 6580990 +events - 6578879 +received_transactions - 5713989 +event_to_state_groups - 4873377 +stream_ordering_to_exterm - 4136285 +current_state_delta_stream - 3770972 +event_search - 3670521 +state_events - 2845082 +room_memberships - 2785854 +cache_invalidation_stream - 2448218 +state_groups - 1255467 +state_group_edges - 1229849 +current_state_events - 1222905 +users_in_public_rooms - 364059 +device_lists_stream - 326903 +user_directory_search - 316433 +``` + +## Show top 20 rooms by new events count in last 1 day: +```sql +SELECT e.room_id, r.name, COUNT(e.event_id) cnt FROM events e +LEFT JOIN room_stats_state r USING (room_id) +WHERE e.origin_server_ts >= DATE_PART('epoch', NOW() - INTERVAL '1 day') * 1000 GROUP BY e.room_id, r.name ORDER BY cnt DESC LIMIT 20; +``` + +## Show top 20 users on homeserver by sent events (messages) at last month: +```sql +SELECT user_id, SUM(total_events) + FROM user_stats_historical + WHERE TO_TIMESTAMP(end_ts/1000) AT TIME ZONE 'UTC' > date_trunc('day', now() - interval '1 month') + GROUP BY user_id + ORDER BY SUM(total_events) DESC + LIMIT 20; +``` + +## Show last 100 messages from needed user, with room names: +```sql +SELECT e.room_id, r.name, e.event_id, e.type, e.content, j.json FROM events e + LEFT JOIN event_json j USING (room_id) + LEFT JOIN room_stats_state r USING (room_id) + WHERE sender = '@LOGIN:example.com' + AND e.type = 'm.room.message' + ORDER BY stream_ordering DESC + LIMIT 100; +``` + +## Show top 20 larger tables by storage size +```sql +SELECT nspname || '.' || relname AS "relation", + pg_size_pretty(pg_total_relation_size(C.oid)) AS "total_size" + FROM pg_class C + LEFT JOIN pg_namespace N ON (N.oid = C.relnamespace) + WHERE nspname NOT IN ('pg_catalog', 'information_schema') + AND C.relkind <> 'i' + AND nspname !~ '^pg_toast' + ORDER BY pg_total_relation_size(C.oid) DESC + LIMIT 20; +``` +### Result example: +``` +public.state_groups_state - 27 GB +public.event_json - 9855 MB +public.events - 3675 MB +public.event_edges - 3404 MB +public.received_transactions - 2745 MB +public.event_reference_hashes - 1864 MB +public.event_auth - 1775 MB +public.stream_ordering_to_exterm - 1663 MB +public.event_search - 1370 MB +public.room_memberships - 1050 MB +public.event_to_state_groups - 948 MB +public.current_state_delta_stream - 711 MB +public.state_events - 611 MB +public.presence_stream - 530 MB +public.current_state_events - 525 MB +public.cache_invalidation_stream - 466 MB +public.receipts_linearized - 279 MB +public.state_groups - 160 MB +public.device_lists_remote_cache - 124 MB +public.state_group_edges - 122 MB +``` + +## Show rooms with names, sorted by events in this rooms +`echo "select event_json.room_id,room_stats_state.name from event_json,room_stats_state where room_stats_state.room_id=event_json.room_id" | psql synapse | sort | uniq -c | sort -n` +### Result example: +``` + 9459 !FPUfgzXYWTKgIrwKxW:matrix.org | This Week in Matrix + 9459 !FPUfgzXYWTKgIrwKxW:matrix.org | This Week in Matrix (TWIM) + 17799 !iDIOImbmXxwNngznsa:matrix.org | Linux in Russian + 18739 !GnEEPYXUhoaHbkFBNX:matrix.org | Riot Android + 23373 !QtykxKocfZaZOUrTwp:matrix.org | Matrix HQ + 39504 !gTQfWzbYncrtNrvEkB:matrix.org | ru.[matrix] + 43601 !iNmaIQExDMeqdITdHH:matrix.org | Riot + 43601 !iNmaIQExDMeqdITdHH:matrix.org | Riot Web/Desktop +``` + +## Lookup room state info by list of room_id +```sql +SELECT rss.room_id, rss.name, rss.canonical_alias, rss.topic, rss.encryption, rsc.joined_members, rsc.local_users_in_room, rss.join_rules +FROM room_stats_state rss +LEFT JOIN room_stats_current rsc USING (room_id) +WHERE room_id IN (WHERE room_id IN ( + '!OGEhHVWSdvArJzumhm:matrix.org', + '!YTvKGNlinIzlkMTVRl:matrix.org' +) +``` \ No newline at end of file -- cgit 1.5.1 From 49e1356ee3d5d72929c91f778b3a231726c1413c Mon Sep 17 00:00:00 2001 From: Shay Date: Thu, 2 Dec 2021 09:46:20 -0800 Subject: Minor cleanup on recently ported doc pages (#11466) * move wiki pages to synapse/docs and add a few titles where necessary * update SUMMARY.md with added pages * add changelog * move incorrectly located newsfragment * update changelog number * snake case added files and update summary.md accordingly * update issue/pr links * update relative links to docs * update changelog to indicate that we moved wiki pages to the docs and state reasoning * requested changes to admin_faq.md * requested changes to database_maintenance_tools.md * requested changes to understanding_synapse_through_graphana_graphs.md * add changelog * fix leftover merge errata * fix unwanted changes from merge * use two spaces between entries * outdent code blocks --- CHANGES.md | 6 ++-- changelog.d/11466.misc | 1 + docs/usage/administration/admin_faq.md | 41 +++++++++++++--------- .../administration/database_maintenance_tools.md | 26 +++----------- ...understanding_synapse_through_grafana_graphs.md | 20 ++++++++--- 5 files changed, 48 insertions(+), 46 deletions(-) create mode 100644 changelog.d/11466.misc (limited to 'docs') diff --git a/CHANGES.md b/CHANGES.md index 2e3f0da961..f398b8e9c5 100644 --- a/CHANGES.md +++ b/CHANGES.md @@ -1,8 +1,9 @@ UNRELEASED ========== -We've decided to move the existing, somewhat stagnant pages from the GitHub wiki +We've decided to move the existing, somewhat stagnant pages from the GitHub wiki to the [documentation website](https://matrix-org.github.io/synapse/latest/). + This was done for two reasons. The first was to ensure that changes are checked by multiple authors before being committed (everyone makes mistakes!) and the second was visibility of the documentation. Not everyone knows that Synapse has some very @@ -10,7 +11,7 @@ useful information hidden away in its GitHub wiki pages. Bringing them to the documentation website should help with visibility, as well as keep all Synapse documentation in one, easily-searchable location. -Note that contributions to the documentation website happen through [GitHub pull +Note that contributions to the documentation website happen through [GitHub pull requests](https://github.com/matrix-org/synapse/pulls). Please visit [#synapse-dev:matrix.org](https://matrix.to/#/#synapse-dev:matrix.org) if you need help with the process! @@ -102,7 +103,6 @@ Internal Changes - Refactor including the bundled relations when serializing an event. ([\#11408](https://github.com/matrix-org/synapse/issues/11408)) - Synapse 1.47.1 (2021-11-23) =========================== diff --git a/changelog.d/11466.misc b/changelog.d/11466.misc new file mode 100644 index 0000000000..4317d017d7 --- /dev/null +++ b/changelog.d/11466.misc @@ -0,0 +1 @@ +Update and clean up recently ported documentation pages. \ No newline at end of file diff --git a/docs/usage/administration/admin_faq.md b/docs/usage/administration/admin_faq.md index 162af0c741..3dcad4bbef 100644 --- a/docs/usage/administration/admin_faq.md +++ b/docs/usage/administration/admin_faq.md @@ -6,27 +6,31 @@ If your server already has an admin account you should use the user admin API to 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. - UPDATE users SET admin = 1 WHERE name = '@foo:bar.com'; - +```sql +UPDATE users SET admin = 1 WHERE name = '@foo:bar.com'; +``` What servers are my server talking to? --- Run this sql query on your db: - - SELECT * FROM destinations; +```sql +SELECT * FROM destinations; +``` What servers are currently participating in this room? --- Run this sql query on your db: - - SELECT DISTINCT split_part(state_key, ':', 2) - FROM current_state_events AS c - INNER JOIN room_memberships AS m USING (room_id, event_id) - WHERE room_id = '!cURbafjkfsMDVwdRDQ:matrix.org' AND membership = 'join'; +```sql +SELECT DISTINCT split_part(state_key, ':', 2) + FROM current_state_events AS c + INNER JOIN room_memberships AS m USING (room_id, event_id) + WHERE room_id = '!cURbafjkfsMDVwdRDQ:matrix.org' AND membership = 'join'; +``` What users are registered on my server? --- - - SELECT NAME from users; +```sql +SELECT NAME from users; +``` Manually resetting passwords: --- @@ -50,13 +54,13 @@ There are two exceptions when it might be sensible to delete your database and s I've stuffed up access to my room, how can I delete it to free up the alias? --- Using the following curl command: - - curl -H 'Authorization: Bearer ' -X DELETE https://matrix.org/_matrix/client/r0/directory/room/ - -\ - can be obtained in riot by looking in the riot settings, down the bottom is: +``` +curl -H 'Authorization: Bearer ' -X DELETE https://matrix.org/_matrix/client/r0/directory/room/ +``` +`` - can be obtained in riot by looking in the riot settings, down the bottom is: Access Token:\ -\ - the room alias, eg. #my_room:matrix.org this possibly needs to be URL encoded also, for example %23my_room%3Amatrix.org +`` - the room alias, eg. #my_room:matrix.org this possibly needs to be URL encoded also, for example %23my_room%3Amatrix.org How can I find the lines corresponding to a given HTTP request in my homeserver log? --- @@ -93,4 +97,7 @@ WHERE g.room_id = s.room_id GROUP BY s.canonical_alias, g.room_id ORDER BY num_rows desc LIMIT 10; -``` \ No newline at end of file +``` + +You can also use the [List Room API](../../admin_api/rooms.md#list-room-api) +and `order_by` `state_events`. diff --git a/docs/usage/administration/database_maintenance_tools.md b/docs/usage/administration/database_maintenance_tools.md index 2c29ccfe69..92b805d413 100644 --- a/docs/usage/administration/database_maintenance_tools.md +++ b/docs/usage/administration/database_maintenance_tools.md @@ -5,32 +5,14 @@ This blog post by Victor Berger explains how to use many of the tools listed on ## [Purge Remote Media API](../../admin_api/media_admin_api.md#purge-remote-media-api) The purge remote media API allows server admins to purge old cached remote media. -#### Purge local media - -There is no purge API for local media because you may be the only one with a copy. If you are sure you want to delete local media you could use something like the following to delete media that hasn't been accessed in a while. - -``` -find /path/to/synapse/media_store/local_content -atime +365 -delete -find /path/to/synapse/media_store/local_thumbnails -atime +365 -delete -``` - -This will delete media that hasn't been accessed in 365 days. - -**Warning, check noatime flag**: You also have to double-check that the filesystem where synapse's media store don't have [noatime flag](https://unix.stackexchange.com/questions/219015/how-to-disable-access-time-settings-in-debian-linux/219017#219017). Check it with `mount`, `noatime` is something that is usually enabled by default to reduce read-write operations in the filesystem for a feature is not so demanded. +## [Purge Local Media API](../../admin_api/media_admin_api.md#delete-local-media) +This API deletes the *local* media from the disk of your own server. ## [Purge History API](../../admin_api/purge_history_api.md) The purge history API allows server admins to purge historic events from their database, reclaiming disk space. -## [synapse_janitor.sql](https://github.com/xwiki-labs/synapse_scripts) - -- this project is [unmantained and dangerous](https://github.com/xwiki-labs/synapse_scripts#unmaintained-and-dangerous) -- USE WITH CAUTION. It may cause database corruption (see https://github.com/matrix-org/synapse/issues/7305 for example). -- ["Our team hasn't used any of these scripts for some time (possibly years) (...) if anyone wants to volunteer to maintain this repo I'd be happy to transfer ownership.](https://github.com/xwiki-labs/synapse_scripts/pull/12#issuecomment-617275345) - -Cleans a synapse Postgres database of deleted messages and abandoned rooms. - ## [synapse-compress-state](https://github.com/matrix-org/rust-synapse-compress-state) Tool for compressing (deduplicating) `state_groups_state` table. -## [SQL for analyzing Synapse PostgreSQL database stats](https://github.com/matrix-org/synapse/wiki/SQL-for-analyzing-Synapse-PostgreSQL-database-stats) -Some easy SQL that reports useful stat about Matrix Synapse database. \ No newline at end of file +## [SQL for analyzing Synapse PostgreSQL database stats](useful_sql_for_admins.md) +Some easy SQL that reports useful stats about your Synapse database. \ No newline at end of file diff --git a/docs/usage/administration/understanding_synapse_through_grafana_graphs.md b/docs/usage/administration/understanding_synapse_through_grafana_graphs.md index bfe4360b4e..c365cc3923 100644 --- a/docs/usage/administration/understanding_synapse_through_grafana_graphs.md +++ b/docs/usage/administration/understanding_synapse_through_grafana_graphs.md @@ -1,6 +1,12 @@ ## Understanding Synapse through Grafana graphs -It is possible monitor much of the internal state of Synapse using [Prometheus](https://prometheus.io) metrics and [Grafana](https://grafana.com/). A guide for configuring Synapse to provide metrics is available [here](../../metrics-howto.md) and information on setting up Grafana is [here](https://github.com/matrix-org/synapse/tree/master/contrib/grafana). In this setup, Prometheus will periodically scrape the information Synapse provides and store a record of it over time. Grafana is then used as an interface to query and present this information through a series of pretty graphs. +It is possible to monitor much of the internal state of Synapse using [Prometheus](https://prometheus.io) +metrics and [Grafana](https://grafana.com/). +A guide for configuring Synapse to provide metrics is available [here](../../metrics-howto.md) +and information on setting up Grafana is [here](https://github.com/matrix-org/synapse/tree/master/contrib/grafana). +In this setup, Prometheus will periodically scrape the information Synapse provides and +store a record of it over time. Grafana is then used as an interface to query and +present this information through a series of pretty graphs. Once you have grafana set up, and assuming you're using [our grafana dashboard template](https://github.com/matrix-org/synapse/blob/master/contrib/grafana/synapse.json), look for the following graphs when debugging a slow/overloaded Synapse: @@ -57,7 +63,7 @@ we should probably consider raising the size of that cache by raising its cache ![image](https://user-images.githubusercontent.com/1342360/82241440-13566680-9934-11ea-8b88-ba468db937ed.png) -Forward extremities are the leaf events at the end of a DAG in a room, aka events that have no children. The more exist in a room, the more [state resolution](https://matrix.org/docs/spec/server_server/r0.1.3#room-state-resolution) that Synapse needs to perform (hint: it's an expensive operation). While Synapse has code to prevent too many of these existing at one time in a room, bugs can sometimes make them crop up again. +Forward extremities are the leaf events at the end of a DAG in a room, aka events that have no children. The more that exist in a room, the more [state resolution](https://spec.matrix.org/v1.1/server-server-api/#room-state-resolution) that Synapse needs to perform (hint: it's an expensive operation). While Synapse has code to prevent too many of these existing at one time in a room, bugs can sometimes make them crop up again. If a room has >10 forward extremities, it's worth checking which room is the culprit and potentially removing them using the SQL queries mentioned in [#1760](https://github.com/matrix-org/synapse/issues/1760). @@ -65,8 +71,14 @@ If a room has >10 forward extremities, it's worth checking which room is the cul ![image](https://user-images.githubusercontent.com/1342360/82241911-da6ac180-9934-11ea-9a0d-a311fe22acd0.png) -Large spikes in garbage collection times (bigger than shown here, I'm talking in the multiple seconds range), can cause lots of problems in Synapse performance. It's more an indicator of problems, and a symptom of other problems though, so check other graphs for what might be causing it. +Large spikes in garbage collection times (bigger than shown here, I'm talking in the +multiple seconds range), can cause lots of problems in Synapse performance. It's more an +indicator of problems, and a symptom of other problems though, so check other graphs for what might be causing it. ## Final Thoughts -If you're still having performance problems with your Synapse instance and you've tried everything you can, it may just be a lack of system resources. Consider adding more CPU and RAM, and make use of [worker mode](../../workers.md) to make use of multiple CPU cores / multiple machines for your homeserver. \ No newline at end of file +If you're still having performance problems with your Synapse instance and you've +tried everything you can, it may just be a lack of system resources. Consider adding +more CPU and RAM, and make use of [worker mode](../../workers.md) +to make use of multiple CPU cores / multiple machines for your homeserver. + -- cgit 1.5.1 From 4eb77965cd016181d2111f37d93526e9bb0434f0 Mon Sep 17 00:00:00 2001 From: Eric Eastwood Date: Fri, 3 Dec 2021 18:25:04 -0600 Subject: Update backward extremity docs to make it clear that it does not indicate whether we have fetched an events' `prev_events` (#11469) Spawning from https://github.com/matrix-org/synapse/pull/9445#discussion_r758958181 Co-authored-by: Richard van der Hoff <1389908+richvdh@users.noreply.github.com> --- changelog.d/11469.doc | 1 + docs/development/room-dag-concepts.md | 16 +++++++--------- 2 files changed, 8 insertions(+), 9 deletions(-) create mode 100644 changelog.d/11469.doc (limited to 'docs') diff --git a/changelog.d/11469.doc b/changelog.d/11469.doc new file mode 100644 index 0000000000..51602aa968 --- /dev/null +++ b/changelog.d/11469.doc @@ -0,0 +1 @@ +Update section about backward extremities in the room DAG concepts doc to correct the misconception about backward extremities indicating whether we have fetched an events' `prev_events`. diff --git a/docs/development/room-dag-concepts.md b/docs/development/room-dag-concepts.md index 5eed72bec6..cbc7cf2949 100644 --- a/docs/development/room-dag-concepts.md +++ b/docs/development/room-dag-concepts.md @@ -38,16 +38,15 @@ Most-recent-in-time events in the DAG which are not referenced by any other even The forward extremities of a room are used as the `prev_events` when the next event is sent. -## Backwards extremity +## Backward extremity The current marker of where we have backfilled up to and will generally be the -oldest-in-time events we know of in the DAG. +`prev_events` of the oldest-in-time events we have in the DAG. This gives a starting point when +backfilling history. -This is an event where we haven't fetched all of the `prev_events` for. - -Once we have fetched all of its `prev_events`, it's unmarked as a backwards -extremity (although we may have formed new backwards extremities from the prev -events during the backfilling process). +When we persist a non-outlier event, we clear it as a backward extremity and set +all of its `prev_events` as the new backward extremities if they aren't already +persisted in the `events` table. ## Outliers @@ -56,8 +55,7 @@ We mark an event as an `outlier` when we haven't figured out the state for the room at that point in the DAG yet. We won't *necessarily* have the `prev_events` of an `outlier` in the database, -but it's entirely possible that we *might*. The status of whether we have all of -the `prev_events` is marked as a [backwards extremity](#backwards-extremity). +but it's entirely possible that we *might*. For example, when we fetch the event auth chain or state for a given event, we mark all of those claimed auth events as outliers because we haven't done the -- cgit 1.5.1 From 8b4b153c9e86c04c7db8c74fde4b6a04becbc461 Mon Sep 17 00:00:00 2001 From: Dirk Klimpel <5740567+dklimpel@users.noreply.github.com> Date: Mon, 6 Dec 2021 17:59:50 +0100 Subject: Add admin API to get some information about federation status (#11407) --- changelog.d/11407.feature | 1 + docs/SUMMARY.md | 1 + docs/usage/administration/admin_api/federation.md | 114 ++++++ synapse/rest/admin/__init__.py | 6 + synapse/rest/admin/federation.py | 135 +++++++ synapse/storage/databases/main/transactions.py | 70 ++++ tests/rest/admin/test_federation.py | 456 ++++++++++++++++++++++ 7 files changed, 783 insertions(+) create mode 100644 changelog.d/11407.feature create mode 100644 docs/usage/administration/admin_api/federation.md create mode 100644 synapse/rest/admin/federation.py create mode 100644 tests/rest/admin/test_federation.py (limited to 'docs') diff --git a/changelog.d/11407.feature b/changelog.d/11407.feature new file mode 100644 index 0000000000..1d21bde98f --- /dev/null +++ b/changelog.d/11407.feature @@ -0,0 +1 @@ +Add admin API to get some information about federation status with remote servers. \ No newline at end of file diff --git a/docs/SUMMARY.md b/docs/SUMMARY.md index 41c8f0fbc9..b05af6d690 100644 --- a/docs/SUMMARY.md +++ b/docs/SUMMARY.md @@ -65,6 +65,7 @@ - [Statistics](admin_api/statistics.md) - [Users](admin_api/user_admin_api.md) - [Server Version](admin_api/version_api.md) + - [Federation](usage/administration/admin_api/federation.md) - [Manhole](manhole.md) - [Monitoring](metrics-howto.md) - [Understanding Synapse Through Grafana Graphs](usage/administration/understanding_synapse_through_grafana_graphs.md) diff --git a/docs/usage/administration/admin_api/federation.md b/docs/usage/administration/admin_api/federation.md new file mode 100644 index 0000000000..8f9535f57b --- /dev/null +++ b/docs/usage/administration/admin_api/federation.md @@ -0,0 +1,114 @@ +# Federation API + +This API allows a server administrator to manage Synapse's federation with other homeservers. + +Note: This API is new, experimental and "subject to change". + +## List of destinations + +This API gets the current destination retry timing info for all remote servers. + +The list contains all the servers with which the server federates, +regardless of whether an error occurred or not. +If an error occurs, it may take up to 20 minutes for the error to be displayed here, +as a complete retry must have failed. + +The API is: + +A standard request with no filtering: + +``` +GET /_synapse/admin/v1/federation/destinations +``` + +A response body like the following is returned: + +```json +{ + "destinations":[ + { + "destination": "matrix.org", + "retry_last_ts": 1557332397936, + "retry_interval": 3000000, + "failure_ts": 1557329397936, + "last_successful_stream_ordering": null + } + ], + "total": 1 +} +``` + +To paginate, check for `next_token` and if present, call the endpoint again +with `from` set to the value of `next_token`. This will return a new page. + +If the endpoint does not return a `next_token` then there are no more destinations +to paginate through. + +**Parameters** + +The following query parameters are available: + +- `from` - Offset in the returned list. Defaults to `0`. +- `limit` - Maximum amount of destinations to return. Defaults to `100`. +- `order_by` - The method in which to sort the returned list of destinations. + Valid values are: + - `destination` - Destinations are ordered alphabetically by remote server name. + This is the default. + - `retry_last_ts` - Destinations are ordered by time of last retry attempt in ms. + - `retry_interval` - Destinations are ordered by how long until next retry in ms. + - `failure_ts` - Destinations are ordered by when the server started failing in ms. + - `last_successful_stream_ordering` - Destinations are ordered by the stream ordering + of the most recent successfully-sent PDU. +- `dir` - Direction of room order. Either `f` for forwards or `b` for backwards. Setting + this value to `b` will reverse the above sort order. Defaults to `f`. + +*Caution:* The database only has an index on the column `destination`. +This means that if a different sort order is used, +this can cause a large load on the database, especially for large environments. + +**Response** + +The following fields are returned in the JSON response body: + +- `destinations` - An array of objects, each containing information about a destination. + Destination objects contain the following fields: + - `destination` - string - Name of the remote server to federate. + - `retry_last_ts` - integer - The last time Synapse tried and failed to reach the + remote server, in ms. This is `0` if the last attempt to communicate with the + remote server was successful. + - `retry_interval` - integer - How long since the last time Synapse tried to reach + the remote server before trying again, in ms. This is `0` if no further retrying occuring. + - `failure_ts` - nullable integer - The first time Synapse tried and failed to reach the + remote server, in ms. This is `null` if communication with the remote server has never failed. + - `last_successful_stream_ordering` - nullable integer - The stream ordering of the most + recent successfully-sent [PDU](understanding_synapse_through_grafana_graphs.md#federation) + to this destination, or `null` if this information has not been tracked yet. +- `next_token`: string representing a positive integer - Indication for pagination. See above. +- `total` - integer - Total number of destinations. + +# Destination Details API + +This API gets the retry timing info for a specific remote server. + +The API is: + +``` +GET /_synapse/admin/v1/federation/destinations/ +``` + +A response body like the following is returned: + +```json +{ + "destination": "matrix.org", + "retry_last_ts": 1557332397936, + "retry_interval": 3000000, + "failure_ts": 1557329397936, + "last_successful_stream_ordering": null +} +``` + +**Response** + +The response fields are the same like in the `destinations` array in +[List of destinations](#list-of-destinations) response. diff --git a/synapse/rest/admin/__init__.py b/synapse/rest/admin/__init__.py index c51a029bf3..c499afd4be 100644 --- a/synapse/rest/admin/__init__.py +++ b/synapse/rest/admin/__init__.py @@ -40,6 +40,10 @@ from synapse.rest.admin.event_reports import ( EventReportDetailRestServlet, EventReportsRestServlet, ) +from synapse.rest.admin.federation import ( + DestinationsRestServlet, + ListDestinationsRestServlet, +) from synapse.rest.admin.groups import DeleteGroupAdminRestServlet from synapse.rest.admin.media import ListMediaInRoom, register_servlets_for_media_repo from synapse.rest.admin.registration_tokens import ( @@ -261,6 +265,8 @@ def register_servlets(hs: "HomeServer", http_server: HttpServer) -> None: ListRegistrationTokensRestServlet(hs).register(http_server) NewRegistrationTokenRestServlet(hs).register(http_server) RegistrationTokenRestServlet(hs).register(http_server) + DestinationsRestServlet(hs).register(http_server) + ListDestinationsRestServlet(hs).register(http_server) # Some servlets only get registered for the main process. if hs.config.worker.worker_app is None: diff --git a/synapse/rest/admin/federation.py b/synapse/rest/admin/federation.py new file mode 100644 index 0000000000..744687be35 --- /dev/null +++ b/synapse/rest/admin/federation.py @@ -0,0 +1,135 @@ +# Copyright 2021 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 logging +from http import HTTPStatus +from typing import TYPE_CHECKING, Tuple + +from synapse.api.errors import Codes, NotFoundError, SynapseError +from synapse.http.servlet import RestServlet, parse_integer, parse_string +from synapse.http.site import SynapseRequest +from synapse.rest.admin._base import admin_patterns, assert_requester_is_admin +from synapse.storage.databases.main.transactions import DestinationSortOrder +from synapse.types import JsonDict + +if TYPE_CHECKING: + from synapse.server import HomeServer + +logger = logging.getLogger(__name__) + + +class ListDestinationsRestServlet(RestServlet): + """Get request to list all destinations. + This needs user to have administrator access in Synapse. + + GET /_synapse/admin/v1/federation/destinations?from=0&limit=10 + + returns: + 200 OK with list of destinations if success otherwise an error. + + The parameters `from` and `limit` are required only for pagination. + By default, a `limit` of 100 is used. + The parameter `destination` can be used to filter by destination. + The parameter `order_by` can be used to order the result. + """ + + PATTERNS = admin_patterns("/federation/destinations$") + + def __init__(self, hs: "HomeServer"): + self._auth = hs.get_auth() + self._store = hs.get_datastore() + + async def on_GET(self, request: SynapseRequest) -> Tuple[int, JsonDict]: + await assert_requester_is_admin(self._auth, request) + + start = parse_integer(request, "from", default=0) + limit = parse_integer(request, "limit", default=100) + + if start < 0: + raise SynapseError( + HTTPStatus.BAD_REQUEST, + "Query parameter from must be a string representing a positive integer.", + errcode=Codes.INVALID_PARAM, + ) + + if limit < 0: + raise SynapseError( + HTTPStatus.BAD_REQUEST, + "Query parameter limit must be a string representing a positive integer.", + errcode=Codes.INVALID_PARAM, + ) + + destination = parse_string(request, "destination") + + order_by = parse_string( + request, + "order_by", + default=DestinationSortOrder.DESTINATION.value, + allowed_values=[dest.value for dest in DestinationSortOrder], + ) + + direction = parse_string(request, "dir", default="f", allowed_values=("f", "b")) + + destinations, total = await self._store.get_destinations_paginate( + start, limit, destination, order_by, direction + ) + response = {"destinations": destinations, "total": total} + if (start + limit) < total: + response["next_token"] = str(start + len(destinations)) + + return HTTPStatus.OK, response + + +class DestinationsRestServlet(RestServlet): + """Get details of a destination. + This needs user to have administrator access in Synapse. + + GET /_synapse/admin/v1/federation/destinations/ + + returns: + 200 OK with details of a destination if success otherwise an error. + """ + + PATTERNS = admin_patterns("/federation/destinations/(?P[^/]+)$") + + def __init__(self, hs: "HomeServer"): + self._auth = hs.get_auth() + self._store = hs.get_datastore() + + async def on_GET( + self, request: SynapseRequest, destination: str + ) -> Tuple[int, JsonDict]: + await assert_requester_is_admin(self._auth, request) + + destination_retry_timings = await self._store.get_destination_retry_timings( + destination + ) + + if not destination_retry_timings: + raise NotFoundError("Unknown destination") + + last_successful_stream_ordering = ( + await self._store.get_destination_last_successful_stream_ordering( + destination + ) + ) + + response = { + "destination": destination, + "failure_ts": destination_retry_timings.failure_ts, + "retry_last_ts": destination_retry_timings.retry_last_ts, + "retry_interval": destination_retry_timings.retry_interval, + "last_successful_stream_ordering": last_successful_stream_ordering, + } + + return HTTPStatus.OK, response diff --git a/synapse/storage/databases/main/transactions.py b/synapse/storage/databases/main/transactions.py index d7dc1f73ac..1622822552 100644 --- a/synapse/storage/databases/main/transactions.py +++ b/synapse/storage/databases/main/transactions.py @@ -14,6 +14,7 @@ import logging from collections import namedtuple +from enum import Enum from typing import TYPE_CHECKING, Iterable, List, Optional, Tuple import attr @@ -44,6 +45,16 @@ _UpdateTransactionRow = namedtuple( ) +class DestinationSortOrder(Enum): + """Enum to define the sorting method used when returning destinations.""" + + DESTINATION = "destination" + RETRY_LAST_TS = "retry_last_ts" + RETTRY_INTERVAL = "retry_interval" + FAILURE_TS = "failure_ts" + LAST_SUCCESSFUL_STREAM_ORDERING = "last_successful_stream_ordering" + + @attr.s(slots=True, frozen=True, auto_attribs=True) class DestinationRetryTimings: """The current destination retry timing info for a remote server.""" @@ -480,3 +491,62 @@ class TransactionWorkerStore(CacheInvalidationWorkerStore): destinations = [row[0] for row in txn] return destinations + + async def get_destinations_paginate( + self, + start: int, + limit: int, + destination: Optional[str] = None, + order_by: str = DestinationSortOrder.DESTINATION.value, + direction: str = "f", + ) -> Tuple[List[JsonDict], int]: + """Function to retrieve a paginated list of destinations. + This will return a json list of destinations and the + total number of destinations matching the filter criteria. + + Args: + start: start number to begin the query from + limit: number of rows to retrieve + destination: search string in destination + order_by: the sort order of the returned list + direction: sort ascending or descending + Returns: + A tuple of a list of mappings from destination to information + and a count of total destinations. + """ + + def get_destinations_paginate_txn( + txn: LoggingTransaction, + ) -> Tuple[List[JsonDict], int]: + order_by_column = DestinationSortOrder(order_by).value + + if direction == "b": + order = "DESC" + else: + order = "ASC" + + args = [] + where_statement = "" + if destination: + args.extend(["%" + destination.lower() + "%"]) + where_statement = "WHERE LOWER(destination) LIKE ?" + + sql_base = f"FROM destinations {where_statement} " + sql = f"SELECT COUNT(*) as total_destinations {sql_base}" + txn.execute(sql, args) + count = txn.fetchone()[0] + + sql = f""" + SELECT destination, retry_last_ts, retry_interval, failure_ts, + last_successful_stream_ordering + {sql_base} + ORDER BY {order_by_column} {order}, destination ASC + LIMIT ? OFFSET ? + """ + txn.execute(sql, args + [limit, start]) + destinations = self.db_pool.cursor_to_dict(txn) + return destinations, count + + return await self.db_pool.runInteraction( + "get_destinations_paginate_txn", get_destinations_paginate_txn + ) diff --git a/tests/rest/admin/test_federation.py b/tests/rest/admin/test_federation.py new file mode 100644 index 0000000000..5188499ef2 --- /dev/null +++ b/tests/rest/admin/test_federation.py @@ -0,0 +1,456 @@ +# Copyright 2021 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 http import HTTPStatus +from typing import List, Optional + +from parameterized import parameterized + +import synapse.rest.admin +from synapse.api.errors import Codes +from synapse.rest.client import login +from synapse.server import HomeServer +from synapse.types import JsonDict + +from tests import unittest + + +class FederationTestCase(unittest.HomeserverTestCase): + servlets = [ + synapse.rest.admin.register_servlets, + login.register_servlets, + ] + + def prepare(self, reactor, clock, hs: HomeServer): + self.store = hs.get_datastore() + self.register_user("admin", "pass", admin=True) + self.admin_user_tok = self.login("admin", "pass") + + self.url = "/_synapse/admin/v1/federation/destinations" + + @parameterized.expand( + [ + ("/_synapse/admin/v1/federation/destinations",), + ("/_synapse/admin/v1/federation/destinations/dummy",), + ] + ) + def test_requester_is_no_admin(self, url: str): + """ + If the user is not a server admin, an error 403 is returned. + """ + + self.register_user("user", "pass", admin=False) + other_user_tok = self.login("user", "pass") + + channel = self.make_request( + "GET", + url, + content={}, + access_token=other_user_tok, + ) + + self.assertEqual(HTTPStatus.FORBIDDEN, channel.code, msg=channel.json_body) + self.assertEqual(Codes.FORBIDDEN, channel.json_body["errcode"]) + + def test_invalid_parameter(self): + """ + If parameters are invalid, an error is returned. + """ + + # negative limit + channel = self.make_request( + "GET", + self.url + "?limit=-5", + access_token=self.admin_user_tok, + ) + + self.assertEqual(HTTPStatus.BAD_REQUEST, channel.code, msg=channel.json_body) + self.assertEqual(Codes.INVALID_PARAM, channel.json_body["errcode"]) + + # negative from + channel = self.make_request( + "GET", + self.url + "?from=-5", + access_token=self.admin_user_tok, + ) + + self.assertEqual(HTTPStatus.BAD_REQUEST, channel.code, msg=channel.json_body) + self.assertEqual(Codes.INVALID_PARAM, channel.json_body["errcode"]) + + # unkown order_by + channel = self.make_request( + "GET", + self.url + "?order_by=bar", + access_token=self.admin_user_tok, + ) + + self.assertEqual(HTTPStatus.BAD_REQUEST, channel.code, msg=channel.json_body) + self.assertEqual(Codes.UNKNOWN, channel.json_body["errcode"]) + + # invalid search order + channel = self.make_request( + "GET", + self.url + "?dir=bar", + access_token=self.admin_user_tok, + ) + + self.assertEqual(HTTPStatus.BAD_REQUEST, channel.code, msg=channel.json_body) + self.assertEqual(Codes.UNKNOWN, channel.json_body["errcode"]) + + # invalid destination + channel = self.make_request( + "GET", + self.url + "/dummy", + access_token=self.admin_user_tok, + ) + + self.assertEqual(HTTPStatus.NOT_FOUND, channel.code, msg=channel.json_body) + self.assertEqual(Codes.NOT_FOUND, channel.json_body["errcode"]) + + def test_limit(self): + """ + Testing list of destinations with limit + """ + + number_destinations = 20 + self._create_destinations(number_destinations) + + channel = self.make_request( + "GET", + self.url + "?limit=5", + access_token=self.admin_user_tok, + ) + + self.assertEqual(HTTPStatus.OK, channel.code, msg=channel.json_body) + self.assertEqual(channel.json_body["total"], number_destinations) + self.assertEqual(len(channel.json_body["destinations"]), 5) + self.assertEqual(channel.json_body["next_token"], "5") + self._check_fields(channel.json_body["destinations"]) + + def test_from(self): + """ + Testing list of destinations with a defined starting point (from) + """ + + number_destinations = 20 + self._create_destinations(number_destinations) + + channel = self.make_request( + "GET", + self.url + "?from=5", + access_token=self.admin_user_tok, + ) + + self.assertEqual(HTTPStatus.OK, channel.code, msg=channel.json_body) + self.assertEqual(channel.json_body["total"], number_destinations) + self.assertEqual(len(channel.json_body["destinations"]), 15) + self.assertNotIn("next_token", channel.json_body) + self._check_fields(channel.json_body["destinations"]) + + def test_limit_and_from(self): + """ + Testing list of destinations with a defined starting point and limit + """ + + number_destinations = 20 + self._create_destinations(number_destinations) + + channel = self.make_request( + "GET", + self.url + "?from=5&limit=10", + access_token=self.admin_user_tok, + ) + + self.assertEqual(HTTPStatus.OK, channel.code, msg=channel.json_body) + self.assertEqual(channel.json_body["total"], number_destinations) + self.assertEqual(channel.json_body["next_token"], "15") + self.assertEqual(len(channel.json_body["destinations"]), 10) + self._check_fields(channel.json_body["destinations"]) + + def test_next_token(self): + """ + Testing that `next_token` appears at the right place + """ + + number_destinations = 20 + self._create_destinations(number_destinations) + + # `next_token` does not appear + # Number of results is the number of entries + channel = self.make_request( + "GET", + self.url + "?limit=20", + access_token=self.admin_user_tok, + ) + + self.assertEqual(HTTPStatus.OK, channel.code, msg=channel.json_body) + self.assertEqual(channel.json_body["total"], number_destinations) + self.assertEqual(len(channel.json_body["destinations"]), number_destinations) + self.assertNotIn("next_token", channel.json_body) + + # `next_token` does not appear + # Number of max results is larger than the number of entries + channel = self.make_request( + "GET", + self.url + "?limit=21", + access_token=self.admin_user_tok, + ) + + self.assertEqual(HTTPStatus.OK, channel.code, msg=channel.json_body) + self.assertEqual(channel.json_body["total"], number_destinations) + self.assertEqual(len(channel.json_body["destinations"]), number_destinations) + self.assertNotIn("next_token", channel.json_body) + + # `next_token` does appear + # Number of max results is smaller than the number of entries + channel = self.make_request( + "GET", + self.url + "?limit=19", + access_token=self.admin_user_tok, + ) + + self.assertEqual(HTTPStatus.OK, channel.code, msg=channel.json_body) + self.assertEqual(channel.json_body["total"], number_destinations) + self.assertEqual(len(channel.json_body["destinations"]), 19) + self.assertEqual(channel.json_body["next_token"], "19") + + # Check + # Set `from` to value of `next_token` for request remaining entries + # `next_token` does not appear + channel = self.make_request( + "GET", + self.url + "?from=19", + access_token=self.admin_user_tok, + ) + + self.assertEqual(HTTPStatus.OK, channel.code, msg=channel.json_body) + self.assertEqual(channel.json_body["total"], number_destinations) + self.assertEqual(len(channel.json_body["destinations"]), 1) + self.assertNotIn("next_token", channel.json_body) + + def test_list_all_destinations(self): + """ + List all destinations. + """ + number_destinations = 5 + self._create_destinations(number_destinations) + + channel = self.make_request( + "GET", + self.url, + {}, + access_token=self.admin_user_tok, + ) + + self.assertEqual(HTTPStatus.OK, channel.code, msg=channel.json_body) + self.assertEqual(number_destinations, len(channel.json_body["destinations"])) + self.assertEqual(number_destinations, channel.json_body["total"]) + + # Check that all fields are available + self._check_fields(channel.json_body["destinations"]) + + def test_order_by(self): + """ + Testing order list with parameter `order_by` + """ + + def _order_test( + expected_destination_list: List[str], + order_by: Optional[str], + dir: Optional[str] = None, + ): + """Request the list of destinations in a certain order. + Assert that order is what we expect + + Args: + expected_destination_list: The list of user_id in the order + we expect to get back from the server + order_by: The type of ordering to give the server + dir: The direction of ordering to give the server + """ + + url = f"{self.url}?" + if order_by is not None: + url += f"order_by={order_by}&" + if dir is not None and dir in ("b", "f"): + url += f"dir={dir}" + channel = self.make_request( + "GET", + url, + access_token=self.admin_user_tok, + ) + self.assertEqual(HTTPStatus.OK, channel.code, msg=channel.json_body) + self.assertEqual(channel.json_body["total"], len(expected_destination_list)) + + returned_order = [ + row["destination"] for row in channel.json_body["destinations"] + ] + self.assertEqual(expected_destination_list, returned_order) + self._check_fields(channel.json_body["destinations"]) + + # create destinations + dest = [ + ("sub-a.example.com", 100, 300, 200, 300), + ("sub-b.example.com", 200, 200, 100, 100), + ("sub-c.example.com", 300, 100, 300, 200), + ] + for ( + destination, + failure_ts, + retry_last_ts, + retry_interval, + last_successful_stream_ordering, + ) in dest: + self.get_success( + self.store.set_destination_retry_timings( + destination, failure_ts, retry_last_ts, retry_interval + ) + ) + self.get_success( + self.store.set_destination_last_successful_stream_ordering( + destination, last_successful_stream_ordering + ) + ) + + # order by default (destination) + _order_test([dest[0][0], dest[1][0], dest[2][0]], None) + _order_test([dest[0][0], dest[1][0], dest[2][0]], None, "f") + _order_test([dest[2][0], dest[1][0], dest[0][0]], None, "b") + + # order by destination + _order_test([dest[0][0], dest[1][0], dest[2][0]], "destination") + _order_test([dest[0][0], dest[1][0], dest[2][0]], "destination", "f") + _order_test([dest[2][0], dest[1][0], dest[0][0]], "destination", "b") + + # order by failure_ts + _order_test([dest[0][0], dest[1][0], dest[2][0]], "failure_ts") + _order_test([dest[0][0], dest[1][0], dest[2][0]], "failure_ts", "f") + _order_test([dest[2][0], dest[1][0], dest[0][0]], "failure_ts", "b") + + # order by retry_last_ts + _order_test([dest[2][0], dest[1][0], dest[0][0]], "retry_last_ts") + _order_test([dest[2][0], dest[1][0], dest[0][0]], "retry_last_ts", "f") + _order_test([dest[0][0], dest[1][0], dest[2][0]], "retry_last_ts", "b") + + # order by retry_interval + _order_test([dest[1][0], dest[0][0], dest[2][0]], "retry_interval") + _order_test([dest[1][0], dest[0][0], dest[2][0]], "retry_interval", "f") + _order_test([dest[2][0], dest[0][0], dest[1][0]], "retry_interval", "b") + + # order by last_successful_stream_ordering + _order_test( + [dest[1][0], dest[2][0], dest[0][0]], "last_successful_stream_ordering" + ) + _order_test( + [dest[1][0], dest[2][0], dest[0][0]], "last_successful_stream_ordering", "f" + ) + _order_test( + [dest[0][0], dest[2][0], dest[1][0]], "last_successful_stream_ordering", "b" + ) + + def test_search_term(self): + """Test that searching for a destination works correctly""" + + def _search_test( + expected_destination: Optional[str], + search_term: str, + ): + """Search for a destination and check that the returned destinationis a match + + Args: + expected_destination: The room_id expected to be returned by the API. + Set to None to expect zero results for the search + search_term: The term to search for room names with + """ + url = f"{self.url}?destination={search_term}" + channel = self.make_request( + "GET", + url.encode("ascii"), + access_token=self.admin_user_tok, + ) + self.assertEqual(HTTPStatus.OK, channel.code, msg=channel.json_body) + + # Check that destinations were returned + self.assertTrue("destinations" in channel.json_body) + self._check_fields(channel.json_body["destinations"]) + destinations = channel.json_body["destinations"] + + # Check that the expected number of destinations were returned + expected_destination_count = 1 if expected_destination else 0 + self.assertEqual(len(destinations), expected_destination_count) + self.assertEqual(channel.json_body["total"], expected_destination_count) + + if expected_destination: + # Check that the first returned destination is correct + self.assertEqual(expected_destination, destinations[0]["destination"]) + + number_destinations = 3 + self._create_destinations(number_destinations) + + # Test searching + _search_test("sub0.example.com", "0") + _search_test("sub0.example.com", "sub0") + + _search_test("sub1.example.com", "1") + _search_test("sub1.example.com", "1.") + + # Test case insensitive + _search_test("sub0.example.com", "SUB0") + + _search_test(None, "foo") + _search_test(None, "bar") + + def test_get_single_destination(self): + """ + Get one specific destinations. + """ + self._create_destinations(5) + + channel = self.make_request( + "GET", + self.url + "/sub0.example.com", + access_token=self.admin_user_tok, + ) + + self.assertEqual(HTTPStatus.OK, channel.code, msg=channel.json_body) + self.assertEqual("sub0.example.com", channel.json_body["destination"]) + + # Check that all fields are available + # convert channel.json_body into a List + self._check_fields([channel.json_body]) + + def _create_destinations(self, number_destinations: int): + """Create a number of destinations + + Args: + number_destinations: Number of destinations to be created + """ + for i in range(0, number_destinations): + dest = f"sub{i}.example.com" + self.get_success(self.store.set_destination_retry_timings(dest, 50, 50, 50)) + self.get_success( + self.store.set_destination_last_successful_stream_ordering(dest, 100) + ) + + def _check_fields(self, content: List[JsonDict]): + """Checks that the expected destination attributes are present in content + + Args: + content: List that is checked for content + """ + for c in content: + self.assertIn("destination", c) + self.assertIn("retry_last_ts", c) + self.assertIn("retry_interval", c) + self.assertIn("failure_ts", c) + self.assertIn("last_successful_stream_ordering", c) -- cgit 1.5.1 From 2f053f3f82ca174cc1c858c75afffae51af8ce0d Mon Sep 17 00:00:00 2001 From: reivilibre Date: Mon, 6 Dec 2021 19:11:43 +0000 Subject: Stabilise support for MSC2918 refresh tokens as they have now been merged into the Matrix specification. (#11435) --- changelog.d/11435.feature | 1 + docs/sample_config.yaml | 38 ++++++++++++++++++++++++++++++++++++++ synapse/config/registration.py | 38 ++++++++++++++++++++++++++++++++++++++ synapse/rest/client/login.py | 29 +++++++++++++---------------- synapse/rest/client/register.py | 23 ++++++++++------------- tests/rest/client/test_auth.py | 30 +++++++++++++++--------------- 6 files changed, 115 insertions(+), 44 deletions(-) create mode 100644 changelog.d/11435.feature (limited to 'docs') diff --git a/changelog.d/11435.feature b/changelog.d/11435.feature new file mode 100644 index 0000000000..9e127fae3c --- /dev/null +++ b/changelog.d/11435.feature @@ -0,0 +1 @@ +Stabilise support for [MSC2918](https://github.com/matrix-org/matrix-doc/blob/main/proposals/2918-refreshtokens.md#msc2918-refresh-tokens) refresh tokens as they have now been merged into the Matrix specification. \ No newline at end of file diff --git a/docs/sample_config.yaml b/docs/sample_config.yaml index ae476d19ac..6696ed5d1e 100644 --- a/docs/sample_config.yaml +++ b/docs/sample_config.yaml @@ -1209,6 +1209,44 @@ oembed: # #session_lifetime: 24h +# Time that an access token remains valid for, if the session is +# using refresh tokens. +# For more information about refresh tokens, please see the manual. +# Note that this only applies to clients which advertise support for +# refresh tokens. +# +# Note also that this is calculated at login time and refresh time: +# changes are not applied to existing sessions until they are refreshed. +# +# By default, this is 5 minutes. +# +#refreshable_access_token_lifetime: 5m + +# Time that a refresh token remains valid for (provided that it is not +# exchanged for another one first). +# This option can be used to automatically log-out inactive sessions. +# Please see the manual for more information. +# +# Note also that this is calculated at login time and refresh time: +# changes are not applied to existing sessions until they are refreshed. +# +# By default, this is infinite. +# +#refresh_token_lifetime: 24h + +# Time that an access token remains valid for, if the session is NOT +# using refresh tokens. +# Please note that not all clients support refresh tokens, so setting +# this to a short value may be inconvenient for some users who will +# then be logged out frequently. +# +# Note also that this is calculated at login time: changes are not applied +# retrospectively to existing sessions for users that have already logged in. +# +# By default, this is infinite. +# +#nonrefreshable_access_token_lifetime: 24h + # The user must provide all of the below types of 3PID when registering. # #registrations_require_3pid: diff --git a/synapse/config/registration.py b/synapse/config/registration.py index 68a4985398..7a059c6dec 100644 --- a/synapse/config/registration.py +++ b/synapse/config/registration.py @@ -220,6 +220,44 @@ class RegistrationConfig(Config): # #session_lifetime: 24h + # Time that an access token remains valid for, if the session is + # using refresh tokens. + # For more information about refresh tokens, please see the manual. + # Note that this only applies to clients which advertise support for + # refresh tokens. + # + # Note also that this is calculated at login time and refresh time: + # changes are not applied to existing sessions until they are refreshed. + # + # By default, this is 5 minutes. + # + #refreshable_access_token_lifetime: 5m + + # Time that a refresh token remains valid for (provided that it is not + # exchanged for another one first). + # This option can be used to automatically log-out inactive sessions. + # Please see the manual for more information. + # + # Note also that this is calculated at login time and refresh time: + # changes are not applied to existing sessions until they are refreshed. + # + # By default, this is infinite. + # + #refresh_token_lifetime: 24h + + # Time that an access token remains valid for, if the session is NOT + # using refresh tokens. + # Please note that not all clients support refresh tokens, so setting + # this to a short value may be inconvenient for some users who will + # then be logged out frequently. + # + # Note also that this is calculated at login time: changes are not applied + # retrospectively to existing sessions for users that have already logged in. + # + # By default, this is infinite. + # + #nonrefreshable_access_token_lifetime: 24h + # The user must provide all of the below types of 3PID when registering. # #registrations_require_3pid: diff --git a/synapse/rest/client/login.py b/synapse/rest/client/login.py index 1b23fa18cf..f9994658c4 100644 --- a/synapse/rest/client/login.py +++ b/synapse/rest/client/login.py @@ -72,7 +72,7 @@ class LoginRestServlet(RestServlet): JWT_TYPE_DEPRECATED = "m.login.jwt" APPSERVICE_TYPE = "m.login.application_service" APPSERVICE_TYPE_UNSTABLE = "uk.half-shot.msc2778.login.application_service" - REFRESH_TOKEN_PARAM = "org.matrix.msc2918.refresh_token" + REFRESH_TOKEN_PARAM = "refresh_token" def __init__(self, hs: "HomeServer"): super().__init__() @@ -90,7 +90,7 @@ class LoginRestServlet(RestServlet): self.saml2_enabled = hs.config.saml2.saml2_enabled self.cas_enabled = hs.config.cas.cas_enabled self.oidc_enabled = hs.config.oidc.oidc_enabled - self._msc2918_enabled = ( + self._refresh_tokens_enabled = ( hs.config.registration.refreshable_access_token_lifetime is not None ) @@ -163,17 +163,16 @@ class LoginRestServlet(RestServlet): async def on_POST(self, request: SynapseRequest) -> Tuple[int, LoginResponse]: login_submission = parse_json_object_from_request(request) - if self._msc2918_enabled: - # Check if this login should also issue a refresh token, as per MSC2918 - should_issue_refresh_token = login_submission.get( - "org.matrix.msc2918.refresh_token", False - ) - if not isinstance(should_issue_refresh_token, bool): - raise SynapseError( - 400, "`org.matrix.msc2918.refresh_token` should be true or false." - ) - else: - should_issue_refresh_token = False + # Check to see if the client requested a refresh token. + client_requested_refresh_token = login_submission.get( + LoginRestServlet.REFRESH_TOKEN_PARAM, False + ) + if not isinstance(client_requested_refresh_token, bool): + raise SynapseError(400, "`refresh_token` should be true or false.") + + should_issue_refresh_token = ( + self._refresh_tokens_enabled and client_requested_refresh_token + ) try: if login_submission["type"] in ( @@ -463,9 +462,7 @@ def _get_auth_flow_dict_for_idp(idp: SsoIdentityProvider) -> JsonDict: class RefreshTokenServlet(RestServlet): - PATTERNS = client_patterns( - "/org.matrix.msc2918.refresh_token/refresh$", releases=(), unstable=True - ) + PATTERNS = (re.compile("^/_matrix/client/v1/refresh$"),) def __init__(self, hs: "HomeServer"): self._auth_handler = hs.get_auth_handler() diff --git a/synapse/rest/client/register.py b/synapse/rest/client/register.py index 11fd6cd24d..8b56c76aed 100644 --- a/synapse/rest/client/register.py +++ b/synapse/rest/client/register.py @@ -419,7 +419,7 @@ class RegisterRestServlet(RestServlet): self.password_policy_handler = hs.get_password_policy_handler() self.clock = hs.get_clock() self._registration_enabled = self.hs.config.registration.enable_registration - self._msc2918_enabled = ( + self._refresh_tokens_enabled = ( hs.config.registration.refreshable_access_token_lifetime is not None ) @@ -445,18 +445,15 @@ class RegisterRestServlet(RestServlet): f"Do not understand membership kind: {kind}", ) - if self._msc2918_enabled: - # Check if this registration should also issue a refresh token, as - # per MSC2918 - should_issue_refresh_token = body.get( - "org.matrix.msc2918.refresh_token", False - ) - if not isinstance(should_issue_refresh_token, bool): - raise SynapseError( - 400, "`org.matrix.msc2918.refresh_token` should be true or false." - ) - else: - should_issue_refresh_token = False + # Check if the clients wishes for this registration to issue a refresh + # token. + client_requested_refresh_tokens = body.get("refresh_token", False) + if not isinstance(client_requested_refresh_tokens, bool): + raise SynapseError(400, "`refresh_token` should be true or false.") + + should_issue_refresh_token = ( + self._refresh_tokens_enabled and client_requested_refresh_tokens + ) # Pull out the provided username and do basic sanity checks early since # the auth layer will store these in sessions. diff --git a/tests/rest/client/test_auth.py b/tests/rest/client/test_auth.py index 7239e1a1b5..aa8ad6d2e1 100644 --- a/tests/rest/client/test_auth.py +++ b/tests/rest/client/test_auth.py @@ -520,7 +520,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): """ return self.make_request( "POST", - "/_matrix/client/unstable/org.matrix.msc2918.refresh_token/refresh", + "/_matrix/client/v1/refresh", {"refresh_token": refresh_token}, ) @@ -557,7 +557,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): login_with_refresh = self.make_request( "POST", "/_matrix/client/r0/login", - {"org.matrix.msc2918.refresh_token": True, **body}, + {"refresh_token": True, **body}, ) self.assertEqual(login_with_refresh.code, 200, login_with_refresh.result) self.assertIn("refresh_token", login_with_refresh.json_body) @@ -588,7 +588,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): "username": "test3", "password": self.user_pass, "auth": {"type": LoginType.DUMMY}, - "org.matrix.msc2918.refresh_token": True, + "refresh_token": True, }, ) self.assertEqual(register_with_refresh.code, 200, register_with_refresh.result) @@ -603,7 +603,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): "type": "m.login.password", "user": "test", "password": self.user_pass, - "org.matrix.msc2918.refresh_token": True, + "refresh_token": True, } login_response = self.make_request( "POST", @@ -614,7 +614,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): refresh_response = self.make_request( "POST", - "/_matrix/client/unstable/org.matrix.msc2918.refresh_token/refresh", + "/_matrix/client/v1/refresh", {"refresh_token": login_response.json_body["refresh_token"]}, ) self.assertEqual(refresh_response.code, 200, refresh_response.result) @@ -641,7 +641,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): "type": "m.login.password", "user": "test", "password": self.user_pass, - "org.matrix.msc2918.refresh_token": True, + "refresh_token": True, } login_response = self.make_request( "POST", @@ -655,7 +655,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): refresh_response = self.make_request( "POST", - "/_matrix/client/unstable/org.matrix.msc2918.refresh_token/refresh", + "/_matrix/client/v1/refresh", {"refresh_token": login_response.json_body["refresh_token"]}, ) self.assertEqual(refresh_response.code, 200, refresh_response.result) @@ -761,7 +761,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): "type": "m.login.password", "user": "test", "password": self.user_pass, - "org.matrix.msc2918.refresh_token": True, + "refresh_token": True, } login_response = self.make_request( "POST", @@ -811,7 +811,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): "type": "m.login.password", "user": "test", "password": self.user_pass, - "org.matrix.msc2918.refresh_token": True, + "refresh_token": True, } login_response = self.make_request( "POST", @@ -868,7 +868,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): "type": "m.login.password", "user": "test", "password": self.user_pass, - "org.matrix.msc2918.refresh_token": True, + "refresh_token": True, } login_response = self.make_request( "POST", @@ -880,7 +880,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): # This first refresh should work properly first_refresh_response = self.make_request( "POST", - "/_matrix/client/unstable/org.matrix.msc2918.refresh_token/refresh", + "/_matrix/client/v1/refresh", {"refresh_token": login_response.json_body["refresh_token"]}, ) self.assertEqual( @@ -890,7 +890,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): # This one as well, since the token in the first one was never used second_refresh_response = self.make_request( "POST", - "/_matrix/client/unstable/org.matrix.msc2918.refresh_token/refresh", + "/_matrix/client/v1/refresh", {"refresh_token": login_response.json_body["refresh_token"]}, ) self.assertEqual( @@ -900,7 +900,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): # This one should not, since the token from the first refresh is not valid anymore third_refresh_response = self.make_request( "POST", - "/_matrix/client/unstable/org.matrix.msc2918.refresh_token/refresh", + "/_matrix/client/v1/refresh", {"refresh_token": first_refresh_response.json_body["refresh_token"]}, ) self.assertEqual( @@ -928,7 +928,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): # Now that the access token from the last valid refresh was used once, refreshing with the N-1 token should fail fourth_refresh_response = self.make_request( "POST", - "/_matrix/client/unstable/org.matrix.msc2918.refresh_token/refresh", + "/_matrix/client/v1/refresh", {"refresh_token": login_response.json_body["refresh_token"]}, ) self.assertEqual( @@ -938,7 +938,7 @@ class RefreshAuthTests(unittest.HomeserverTestCase): # But refreshing from the last valid refresh token still works fifth_refresh_response = self.make_request( "POST", - "/_matrix/client/unstable/org.matrix.msc2918.refresh_token/refresh", + "/_matrix/client/v1/refresh", {"refresh_token": second_refresh_response.json_body["refresh_token"]}, ) self.assertEqual( -- cgit 1.5.1