diff options
58 files changed, 398 insertions, 184 deletions
diff --git a/CHANGES.rst b/CHANGES.rst index a7ed49e105..38372381ac 100644 --- a/CHANGES.rst +++ b/CHANGES.rst @@ -1,11 +1,89 @@ -Unreleased -========== +Changes in synapse v0.27.2 (2018-03-26) +======================================= + +Bug fixes: + +* Fix bug which broke TCP replication between workers (PR #3015) + + +Changes in synapse v0.27.1 (2018-03-26) +======================================= + +Meta release as v0.27.0 temporarily pointed to the wrong commit + + +Changes in synapse v0.27.0 (2018-03-26) +======================================= + +No changes since v0.27.0-rc2 + + +Changes in synapse v0.27.0-rc2 (2018-03-19) +=========================================== + +Pulls in v0.26.1 + +Bug fixes: + +* Fix bug introduced in v0.27.0-rc1 that causes much increased memory usage in state cache (PR #3005) -synctl no longer starts the main synapse when using ``-a`` option with workers. -A new worker file should be added with ``worker_app: synapse.app.homeserver``. + +Changes in synapse v0.26.1 (2018-03-15) +======================================= + +Bug fixes: + +* Fix bug where an invalid event caused server to stop functioning correctly, + due to parsing and serializing bugs in ujson library (PR #3008) + + +Changes in synapse v0.27.0-rc1 (2018-03-14) +=========================================== + +The common case for running Synapse is not to run separate workers, but for those that do, be aware that synctl no longer starts the main synapse when using ``-a`` option with workers. A new worker file should be added with ``worker_app: synapse.app.homeserver``. This release also begins the process of renaming a number of the metrics reported to prometheus. See `docs/metrics-howto.rst <docs/metrics-howto.rst#block-and-response-metrics-renamed-for-0-27-0>`_. +Note that the v0.28.0 release will remove the deprecated metric names. + +Features: + +* Add ability for ASes to override message send time (PR #2754) +* Add support for custom storage providers for media repository (PR #2867, #2777, #2783, #2789, #2791, #2804, #2812, #2814, #2857, #2868, #2767) +* Add purge API features, see `docs/admin_api/purge_history_api.rst <docs/admin_api/purge_history_api.rst>`_ for full details (PR #2858, #2867, #2882, #2946, #2962, #2943) +* Add support for whitelisting 3PIDs that users can register. (PR #2813) +* Add ``/room/{id}/event/{id}`` API (PR #2766) +* Add an admin API to get all the media in a room (PR #2818) Thanks to @turt2live! +* Add ``federation_domain_whitelist`` option (PR #2820, #2821) + + +Changes: + +* Continue to factor out processing from main process and into worker processes. See updated `docs/workers.rst <docs/workers.rst>`_ (PR #2892 - #2904, #2913, #2920 - #2926, #2947, #2847, #2854, #2872, #2873, #2874, #2928, #2929, #2934, #2856, #2976 - #2984, #2987 - #2989, #2991 - #2993, #2995, #2784) +* Ensure state cache is used when persisting events (PR #2864, #2871, #2802, #2835, #2836, #2841, #2842, #2849) +* Change the default config to bind on both IPv4 and IPv6 on all platforms (PR #2435) Thanks to @silkeh! +* No longer require a specific version of saml2 (PR #2695) Thanks to @okurz! +* Remove ``verbosity``/``log_file`` from generated config (PR #2755) +* Add and improve metrics and logging (PR #2770, #2778, #2785, #2786, #2787, #2793, #2794, #2795, #2809, #2810, #2833, #2834, #2844, #2965, #2927, #2975, #2790, #2796, #2838) +* When using synctl with workers, don't start the main synapse automatically (PR #2774) +* Minor performance improvements (PR #2773, #2792) +* Use a connection pool for non-federation outbound connections (PR #2817) +* Make it possible to run unit tests against postgres (PR #2829) +* Update pynacl dependency to 1.2.1 or higher (PR #2888) Thanks to @bachp! +* Remove ability for AS users to call /events and /sync (PR #2948) +* Use bcrypt.checkpw (PR #2949) Thanks to @krombel! + +Bug fixes: + +* Fix broken ``ldap_config`` config option (PR #2683) Thanks to @seckrv! +* Fix error message when user is not allowed to unban (PR #2761) Thanks to @turt2live! +* Fix publicised groups GET API (singular) over federation (PR #2772) +* Fix user directory when using ``user_directory_search_all_users`` config option (PR #2803, #2831) +* Fix error on ``/publicRooms`` when no rooms exist (PR #2827) +* Fix bug in quarantine_media (PR #2837) +* Fix url_previews when no Content-Type is returned from URL (PR #2845) +* Fix rare race in sync API when joining room (PR #2944) +* Fix slow event search, switch back from GIST to GIN indexes (PR #2769, #2848) Changes in synapse v0.26.0 (2018-01-05) diff --git a/README.rst b/README.rst index 76fe2e4139..ef27b92ddd 100644 --- a/README.rst +++ b/README.rst @@ -354,6 +354,10 @@ https://matrix.org/docs/projects/try-matrix-now.html (or build your own with one Fedora ------ +Synapse is in the Fedora repositories as ``matrix-synapse``:: + + sudo dnf install matrix-synapse + Oleg Girko provides Fedora RPMs at https://obs.infoserver.lv/project/monitor/matrix-synapse @@ -890,6 +894,17 @@ This should end with a 'PASSED' result:: PASSED (successes=143) +Running the Integration Tests +============================= + +Synapse is accompanied by `SyTest <https://github.com/matrix-org/sytest>`_, +a Matrix homeserver integration testing suite, which uses HTTP requests to +access the API as a Matrix client would. It is able to run Synapse directly from +the source tree, so installation of the server is not required. + +Testing with SyTest is recommended for verifying that changes related to the +Client-Server API are functioning correctly. See the `installation instructions +<https://github.com/matrix-org/sytest#installing>`_ for details. Building Internal API Documentation =================================== diff --git a/UPGRADE.rst b/UPGRADE.rst index 2efe7ea60f..f6bb1070b1 100644 --- a/UPGRADE.rst +++ b/UPGRADE.rst @@ -48,6 +48,18 @@ returned by the Client-Server API: # configured on port 443. curl -kv https://<host.name>/_matrix/client/versions 2>&1 | grep "Server:" +Upgrading to $NEXT_VERSION +==================== + +This release expands the anonymous usage stats sent if the opt-in +``report_stats`` configuration is set to ``true``. We now capture RSS memory +and cpu use at a very coarse level. This requires administrators to install +the optional ``psutil`` python module. + +We would appreciate it if you could assist by ensuring this module is available +and ``report_stats`` is enabled. This will let us see if performance changes to +synapse are having an impact to the general community. + Upgrading to v0.15.0 ==================== diff --git a/docs/admin_api/purge_history_api.rst b/docs/admin_api/purge_history_api.rst index ea2922da5c..2da833c827 100644 --- a/docs/admin_api/purge_history_api.rst +++ b/docs/admin_api/purge_history_api.rst @@ -16,9 +16,11 @@ including an ``access_token`` of a server admin. By default, events sent by local users are not deleted, as they may represent the only copies of this content in existence. (Events sent by remote users are -deleted, and room state data before the cutoff is always removed). +deleted.) -To delete local events as well, set ``delete_local_events`` in the body: +Room state data (such as joins, leaves, topic) is always preserved. + +To delete local message events as well, set ``delete_local_events`` in the body: .. code:: json diff --git a/docs/workers.rst b/docs/workers.rst index dee04bbf3e..80f8d2181a 100644 --- a/docs/workers.rst +++ b/docs/workers.rst @@ -230,7 +230,7 @@ file. For example:: ``synapse.app.event_creator`` ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Handles non-state event creation. It can handle REST endpoints matching: +Handles non-state event creation. It can handle REST endpoints matching:: ^/_matrix/client/(api/v1|r0|unstable)/rooms/.*/send diff --git a/synapse/__init__.py b/synapse/__init__.py index ef8853bd24..a9d5198aba 100644 --- a/synapse/__init__.py +++ b/synapse/__init__.py @@ -16,4 +16,4 @@ """ This is a reference implementation of a Matrix home server. """ -__version__ = "0.26.0" +__version__ = "0.27.2" diff --git a/synapse/api/errors.py b/synapse/api/errors.py index aa15f73f36..bee59e80dd 100644 --- a/synapse/api/errors.py +++ b/synapse/api/errors.py @@ -15,9 +15,10 @@ """Contains exceptions and error codes.""" -import json import logging +import simplejson as json + logger = logging.getLogger(__name__) diff --git a/synapse/api/filtering.py b/synapse/api/filtering.py index 83206348e5..db43219d24 100644 --- a/synapse/api/filtering.py +++ b/synapse/api/filtering.py @@ -17,7 +17,7 @@ from synapse.storage.presence import UserPresenceState from synapse.types import UserID, RoomID from twisted.internet import defer -import ujson as json +import simplejson as json import jsonschema from jsonschema import FormatChecker diff --git a/synapse/app/appservice.py b/synapse/app/appservice.py index c6fe4516d1..f2540023a7 100644 --- a/synapse/app/appservice.py +++ b/synapse/app/appservice.py @@ -36,7 +36,7 @@ from synapse.util.logcontext import LoggingContext, preserve_fn from synapse.util.manhole import manhole from synapse.util.versionstring import get_version_string from twisted.internet import reactor -from twisted.web.resource import Resource +from twisted.web.resource import NoResource logger = logging.getLogger("synapse.app.appservice") @@ -64,7 +64,7 @@ class AppserviceServer(HomeServer): if name == "metrics": resources[METRICS_PREFIX] = MetricsResource(self) - root_resource = create_resource_tree(resources, Resource()) + root_resource = create_resource_tree(resources, NoResource()) _base.listen_tcp( bind_addresses, diff --git a/synapse/app/client_reader.py b/synapse/app/client_reader.py index 0a8ce9bc66..267d34c881 100644 --- a/synapse/app/client_reader.py +++ b/synapse/app/client_reader.py @@ -44,7 +44,7 @@ from synapse.util.logcontext import LoggingContext from synapse.util.manhole import manhole from synapse.util.versionstring import get_version_string from twisted.internet import reactor -from twisted.web.resource import Resource +from twisted.web.resource import NoResource logger = logging.getLogger("synapse.app.client_reader") @@ -88,7 +88,7 @@ class ClientReaderServer(HomeServer): "/_matrix/client/api/v1": resource, }) - root_resource = create_resource_tree(resources, Resource()) + root_resource = create_resource_tree(resources, NoResource()) _base.listen_tcp( bind_addresses, diff --git a/synapse/app/event_creator.py b/synapse/app/event_creator.py index 172e989b54..b915d12d53 100644 --- a/synapse/app/event_creator.py +++ b/synapse/app/event_creator.py @@ -52,7 +52,7 @@ from synapse.util.logcontext import LoggingContext from synapse.util.manhole import manhole from synapse.util.versionstring import get_version_string from twisted.internet import reactor -from twisted.web.resource import Resource +from twisted.web.resource import NoResource logger = logging.getLogger("synapse.app.event_creator") @@ -104,7 +104,7 @@ class EventCreatorServer(HomeServer): "/_matrix/client/api/v1": resource, }) - root_resource = create_resource_tree(resources, Resource()) + root_resource = create_resource_tree(resources, NoResource()) _base.listen_tcp( bind_addresses, diff --git a/synapse/app/federation_reader.py b/synapse/app/federation_reader.py index 20d157911b..c1dc66dd17 100644 --- a/synapse/app/federation_reader.py +++ b/synapse/app/federation_reader.py @@ -41,7 +41,7 @@ from synapse.util.logcontext import LoggingContext from synapse.util.manhole import manhole from synapse.util.versionstring import get_version_string from twisted.internet import reactor -from twisted.web.resource import Resource +from twisted.web.resource import NoResource logger = logging.getLogger("synapse.app.federation_reader") @@ -77,7 +77,7 @@ class FederationReaderServer(HomeServer): FEDERATION_PREFIX: TransportLayerServer(self), }) - root_resource = create_resource_tree(resources, Resource()) + root_resource = create_resource_tree(resources, NoResource()) _base.listen_tcp( bind_addresses, diff --git a/synapse/app/federation_sender.py b/synapse/app/federation_sender.py index f760826d27..0cc3331519 100644 --- a/synapse/app/federation_sender.py +++ b/synapse/app/federation_sender.py @@ -42,7 +42,7 @@ from synapse.util.logcontext import LoggingContext, preserve_fn from synapse.util.manhole import manhole from synapse.util.versionstring import get_version_string from twisted.internet import defer, reactor -from twisted.web.resource import Resource +from twisted.web.resource import NoResource logger = logging.getLogger("synapse.app.federation_sender") @@ -91,7 +91,7 @@ class FederationSenderServer(HomeServer): if name == "metrics": resources[METRICS_PREFIX] = MetricsResource(self) - root_resource = create_resource_tree(resources, Resource()) + root_resource = create_resource_tree(resources, NoResource()) _base.listen_tcp( bind_addresses, diff --git a/synapse/app/frontend_proxy.py b/synapse/app/frontend_proxy.py index 816c080d18..de889357c3 100644 --- a/synapse/app/frontend_proxy.py +++ b/synapse/app/frontend_proxy.py @@ -44,7 +44,7 @@ from synapse.util.logcontext import LoggingContext from synapse.util.manhole import manhole from synapse.util.versionstring import get_version_string from twisted.internet import defer, reactor -from twisted.web.resource import Resource +from twisted.web.resource import NoResource logger = logging.getLogger("synapse.app.frontend_proxy") @@ -142,7 +142,7 @@ class FrontendProxyServer(HomeServer): "/_matrix/client/api/v1": resource, }) - root_resource = create_resource_tree(resources, Resource()) + root_resource = create_resource_tree(resources, NoResource()) _base.listen_tcp( bind_addresses, diff --git a/synapse/app/homeserver.py b/synapse/app/homeserver.py index e477c7ced6..b935beb974 100755 --- a/synapse/app/homeserver.py +++ b/synapse/app/homeserver.py @@ -56,7 +56,7 @@ from synapse.util.rlimit import change_resource_limit from synapse.util.versionstring import get_version_string from twisted.application import service from twisted.internet import defer, reactor -from twisted.web.resource import EncodingResourceWrapper, Resource +from twisted.web.resource import EncodingResourceWrapper, NoResource from twisted.web.server import GzipEncoderFactory from twisted.web.static import File @@ -126,7 +126,7 @@ class SynapseHomeServer(HomeServer): if WEB_CLIENT_PREFIX in resources: root_resource = RootRedirect(WEB_CLIENT_PREFIX) else: - root_resource = Resource() + root_resource = NoResource() root_resource = create_resource_tree(resources, root_resource) @@ -402,6 +402,10 @@ def run(hs): stats = {} + # Contains the list of processes we will be monitoring + # currently either 0 or 1 + stats_process = [] + @defer.inlineCallbacks def phone_stats_home(): logger.info("Gathering stats for reporting") @@ -428,6 +432,13 @@ def run(hs): daily_sent_messages = yield hs.get_datastore().count_daily_sent_messages() stats["daily_sent_messages"] = daily_sent_messages + if len(stats_process) > 0: + stats["memory_rss"] = 0 + stats["cpu_average"] = 0 + for process in stats_process: + stats["memory_rss"] += process.memory_info().rss + stats["cpu_average"] += int(process.cpu_percent(interval=None)) + logger.info("Reporting stats to matrix.org: %s" % (stats,)) try: yield hs.get_simple_http_client().put_json( @@ -437,10 +448,32 @@ def run(hs): except Exception as e: logger.warn("Error reporting stats: %s", e) + def performance_stats_init(): + try: + import psutil + process = psutil.Process() + # Ensure we can fetch both, and make the initial request for cpu_percent + # so the next request will use this as the initial point. + process.memory_info().rss + process.cpu_percent(interval=None) + logger.info("report_stats can use psutil") + stats_process.append(process) + except (ImportError, AttributeError): + logger.warn( + "report_stats enabled but psutil is not installed or incorrect version." + " Disabling reporting of memory/cpu stats." + " Ensuring psutil is available will help matrix.org track performance" + " changes across releases." + ) + if hs.config.report_stats: logger.info("Scheduling stats reporting for 3 hour intervals") clock.looping_call(phone_stats_home, 3 * 60 * 60 * 1000) + # We need to defer this init for the cases that we daemonize + # otherwise the process ID we get is that of the non-daemon process + clock.call_later(0, performance_stats_init) + # We wait 5 minutes to send the first set of stats as the server can # be quite busy the first few minutes clock.call_later(5 * 60, phone_stats_home) diff --git a/synapse/app/media_repository.py b/synapse/app/media_repository.py index 84c5791b3b..fc8282bbc1 100644 --- a/synapse/app/media_repository.py +++ b/synapse/app/media_repository.py @@ -43,7 +43,7 @@ from synapse.util.logcontext import LoggingContext from synapse.util.manhole import manhole from synapse.util.versionstring import get_version_string from twisted.internet import reactor -from twisted.web.resource import Resource +from twisted.web.resource import NoResource logger = logging.getLogger("synapse.app.media_repository") @@ -84,7 +84,7 @@ class MediaRepositoryServer(HomeServer): ), }) - root_resource = create_resource_tree(resources, Resource()) + root_resource = create_resource_tree(resources, NoResource()) _base.listen_tcp( bind_addresses, diff --git a/synapse/app/pusher.py b/synapse/app/pusher.py index 98a4a7c62c..d5c3a85195 100644 --- a/synapse/app/pusher.py +++ b/synapse/app/pusher.py @@ -37,7 +37,7 @@ from synapse.util.logcontext import LoggingContext, preserve_fn from synapse.util.manhole import manhole from synapse.util.versionstring import get_version_string from twisted.internet import defer, reactor -from twisted.web.resource import Resource +from twisted.web.resource import NoResource logger = logging.getLogger("synapse.app.pusher") @@ -94,7 +94,7 @@ class PusherServer(HomeServer): if name == "metrics": resources[METRICS_PREFIX] = MetricsResource(self) - root_resource = create_resource_tree(resources, Resource()) + root_resource = create_resource_tree(resources, NoResource()) _base.listen_tcp( bind_addresses, diff --git a/synapse/app/synchrotron.py b/synapse/app/synchrotron.py index abe91dcfbd..508b66613d 100644 --- a/synapse/app/synchrotron.py +++ b/synapse/app/synchrotron.py @@ -56,7 +56,7 @@ from synapse.util.manhole import manhole from synapse.util.stringutils import random_string from synapse.util.versionstring import get_version_string from twisted.internet import defer, reactor -from twisted.web.resource import Resource +from twisted.web.resource import NoResource logger = logging.getLogger("synapse.app.synchrotron") @@ -269,7 +269,7 @@ class SynchrotronServer(HomeServer): "/_matrix/client/api/v1": resource, }) - root_resource = create_resource_tree(resources, Resource()) + root_resource = create_resource_tree(resources, NoResource()) _base.listen_tcp( bind_addresses, diff --git a/synapse/app/user_dir.py b/synapse/app/user_dir.py index 494ccb702c..5f845e80d1 100644 --- a/synapse/app/user_dir.py +++ b/synapse/app/user_dir.py @@ -43,7 +43,7 @@ from synapse.util.logcontext import LoggingContext, preserve_fn from synapse.util.manhole import manhole from synapse.util.versionstring import get_version_string from twisted.internet import reactor -from twisted.web.resource import Resource +from twisted.web.resource import NoResource logger = logging.getLogger("synapse.app.user_dir") @@ -116,7 +116,7 @@ class UserDirectoryServer(HomeServer): "/_matrix/client/api/v1": resource, }) - root_resource = create_resource_tree(resources, Resource()) + root_resource = create_resource_tree(resources, NoResource()) _base.listen_tcp( bind_addresses, diff --git a/synapse/config/registration.py b/synapse/config/registration.py index 336959094b..c5384b3ad4 100644 --- a/synapse/config/registration.py +++ b/synapse/config/registration.py @@ -77,7 +77,9 @@ class RegistrationConfig(Config): # Set the number of bcrypt rounds used to generate password hash. # Larger numbers increase the work factor needed to generate the hash. - # The default number of rounds is 12. + # The default number is 12 (which equates to 2^12 rounds). + # N.B. that increasing this will exponentially increase the time required + # to register or login - e.g. 24 => 2^24 rounds which will take >20 mins. bcrypt_rounds: 12 # Allows users to register as guests without a password/email/etc, and diff --git a/synapse/handlers/e2e_keys.py b/synapse/handlers/e2e_keys.py index 31b1ece13e..325c0c4a9f 100644 --- a/synapse/handlers/e2e_keys.py +++ b/synapse/handlers/e2e_keys.py @@ -1,5 +1,6 @@ # -*- coding: utf-8 -*- # Copyright 2016 OpenMarket Ltd +# Copyright 2018 New Vector Ltd # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. @@ -13,7 +14,7 @@ # See the License for the specific language governing permissions and # limitations under the License. -import ujson as json +import simplejson as json import logging from canonicaljson import encode_canonical_json @@ -134,23 +135,8 @@ class E2eKeysHandler(object): if user_id in destination_query: results[user_id] = keys - except CodeMessageException as e: - failures[destination] = { - "status": e.code, "message": e.message - } - except NotRetryingDestination as e: - failures[destination] = { - "status": 503, "message": "Not ready for retry", - } - except FederationDeniedError as e: - failures[destination] = { - "status": 403, "message": "Federation Denied", - } except Exception as e: - # include ConnectionRefused and other errors - failures[destination] = { - "status": 503, "message": e.message - } + failures[destination] = _exception_to_failure(e) yield make_deferred_yieldable(defer.gatherResults([ preserve_fn(do_remote_query)(destination) @@ -252,19 +238,8 @@ class E2eKeysHandler(object): for user_id, keys in remote_result["one_time_keys"].items(): if user_id in device_keys: json_result[user_id] = keys - except CodeMessageException as e: - failures[destination] = { - "status": e.code, "message": e.message - } - except NotRetryingDestination as e: - failures[destination] = { - "status": 503, "message": "Not ready for retry", - } except Exception as e: - # include ConnectionRefused and other errors - failures[destination] = { - "status": 503, "message": e.message - } + failures[destination] = _exception_to_failure(e) yield make_deferred_yieldable(defer.gatherResults([ preserve_fn(claim_client_keys)(destination) @@ -362,6 +337,31 @@ class E2eKeysHandler(object): ) +def _exception_to_failure(e): + if isinstance(e, CodeMessageException): + return { + "status": e.code, "message": e.message, + } + + if isinstance(e, NotRetryingDestination): + return { + "status": 503, "message": "Not ready for retry", + } + + if isinstance(e, FederationDeniedError): + return { + "status": 403, "message": "Federation Denied", + } + + # include ConnectionRefused and other errors + # + # Note that some Exceptions (notably twisted's ResponseFailed etc) don't + # give a string for e.message, which simplejson then fails to serialize. + return { + "status": 503, "message": str(e.message), + } + + def _one_time_keys_match(old_key_json, new_key): old_key = json.loads(old_key_json) diff --git a/synapse/handlers/identity.py b/synapse/handlers/identity.py index 9efcdff1d6..91a0898860 100644 --- a/synapse/handlers/identity.py +++ b/synapse/handlers/identity.py @@ -15,6 +15,11 @@ # limitations under the License. """Utilities for interacting with Identity Servers""" + +import logging + +import simplejson as json + from twisted.internet import defer from synapse.api.errors import ( @@ -24,9 +29,6 @@ from ._base import BaseHandler from synapse.util.async import run_on_reactor from synapse.api.errors import SynapseError, Codes -import json -import logging - logger = logging.getLogger(__name__) diff --git a/synapse/handlers/message.py b/synapse/handlers/message.py index 4f97c8db79..6de6e13b7b 100644 --- a/synapse/handlers/message.py +++ b/synapse/handlers/message.py @@ -27,7 +27,7 @@ from synapse.types import ( from synapse.util.async import run_on_reactor, ReadWriteLock, Limiter from synapse.util.logcontext import preserve_fn, run_in_background from synapse.util.metrics import measure_func -from synapse.util.frozenutils import unfreeze +from synapse.util.frozenutils import frozendict_json_encoder from synapse.util.stringutils import random_string from synapse.visibility import filter_events_for_client from synapse.replication.http.send_event import send_event_to_master @@ -38,7 +38,7 @@ from canonicaljson import encode_canonical_json import logging import random -import ujson +import simplejson logger = logging.getLogger(__name__) @@ -678,8 +678,8 @@ class EventCreationHandler(object): # Ensure that we can round trip before trying to persist in db try: - dump = ujson.dumps(unfreeze(event.content)) - ujson.loads(dump) + dump = frozendict_json_encoder.encode(event.content) + simplejson.loads(dump) except Exception: logger.exception("Failed to encode content: %r", event.content) raise diff --git a/synapse/handlers/register.py b/synapse/handlers/register.py index ed5939880a..dd03705279 100644 --- a/synapse/handlers/register.py +++ b/synapse/handlers/register.py @@ -24,7 +24,7 @@ from synapse.api.errors import ( from synapse.http.client import CaptchaServerHttpClient from synapse import types from synapse.types import UserID -from synapse.util.async import run_on_reactor +from synapse.util.async import run_on_reactor, Linearizer from synapse.util.threepids import check_3pid_allowed from ._base import BaseHandler @@ -46,6 +46,10 @@ class RegistrationHandler(BaseHandler): self.macaroon_gen = hs.get_macaroon_generator() + self._generate_user_id_linearizer = Linearizer( + name="_generate_user_id_linearizer", + ) + @defer.inlineCallbacks def check_username(self, localpart, guest_access_token=None, assigned_user_id=None): @@ -345,9 +349,11 @@ class RegistrationHandler(BaseHandler): @defer.inlineCallbacks def _generate_user_id(self, reseed=False): if reseed or self._next_generated_user_id is None: - self._next_generated_user_id = ( - yield self.store.find_next_generated_user_id_localpart() - ) + with (yield self._generate_user_id_linearizer.queue(())): + if reseed or self._next_generated_user_id is None: + self._next_generated_user_id = ( + yield self.store.find_next_generated_user_id_localpart() + ) id = self._next_generated_user_id self._next_generated_user_id += 1 diff --git a/synapse/http/server.py b/synapse/http/server.py index 4b567215c8..f19c068ef6 100644 --- a/synapse/http/server.py +++ b/synapse/http/server.py @@ -37,7 +37,7 @@ from twisted.web.util import redirectTo import collections import logging import urllib -import ujson +import simplejson logger = logging.getLogger(__name__) @@ -461,8 +461,7 @@ def respond_with_json(request, code, json_object, send_cors=False, if canonical_json or synapse.events.USE_FROZEN_DICTS: json_bytes = encode_canonical_json(json_object) else: - # ujson doesn't like frozen_dicts. - json_bytes = ujson.dumps(json_object, ensure_ascii=False) + json_bytes = simplejson.dumps(json_object) return respond_with_json_bytes( request, code, json_bytes, @@ -489,6 +488,7 @@ def respond_with_json_bytes(request, code, json_bytes, send_cors=False, request.setHeader(b"Content-Type", b"application/json") request.setHeader(b"Server", version_string) request.setHeader(b"Content-Length", b"%d" % (len(json_bytes),)) + request.setHeader(b"Cache-Control", b"no-cache, no-store, must-revalidate") if send_cors: set_cors_headers(request) diff --git a/synapse/python_dependencies.py b/synapse/python_dependencies.py index 91179ce532..40eedb63cb 100644 --- a/synapse/python_dependencies.py +++ b/synapse/python_dependencies.py @@ -34,7 +34,6 @@ REQUIREMENTS = { "bcrypt": ["bcrypt>=3.1.0"], "pillow": ["PIL"], "pydenticon": ["pydenticon"], - "ujson": ["ujson"], "blist": ["blist"], "pysaml2>=3.0.0": ["saml2>=3.0.0"], "pymacaroons-pynacl": ["pymacaroons"], diff --git a/synapse/replication/tcp/commands.py b/synapse/replication/tcp/commands.py index 171227cce2..12aac3cc6b 100644 --- a/synapse/replication/tcp/commands.py +++ b/synapse/replication/tcp/commands.py @@ -19,11 +19,13 @@ allowed to be sent by which side. """ import logging -import ujson as json +import simplejson logger = logging.getLogger(__name__) +_json_encoder = simplejson.JSONEncoder(namedtuple_as_object=False) + class Command(object): """The base command class. @@ -100,14 +102,14 @@ class RdataCommand(Command): return cls( stream_name, None if token == "batch" else int(token), - json.loads(row_json) + simplejson.loads(row_json) ) def to_line(self): return " ".join(( self.stream_name, str(self.token) if self.token is not None else "batch", - json.dumps(self.row), + _json_encoder.encode(self.row), )) @@ -298,10 +300,12 @@ class InvalidateCacheCommand(Command): def from_line(cls, line): cache_func, keys_json = line.split(" ", 1) - return cls(cache_func, json.loads(keys_json)) + return cls(cache_func, simplejson.loads(keys_json)) def to_line(self): - return " ".join((self.cache_func, json.dumps(self.keys))) + return " ".join(( + self.cache_func, _json_encoder.encode(self.keys), + )) class UserIpCommand(Command): @@ -325,14 +329,14 @@ class UserIpCommand(Command): def from_line(cls, line): user_id, jsn = line.split(" ", 1) - access_token, ip, user_agent, device_id, last_seen = json.loads(jsn) + access_token, ip, user_agent, device_id, last_seen = simplejson.loads(jsn) return cls( user_id, access_token, ip, user_agent, device_id, last_seen ) def to_line(self): - return self.user_id + " " + json.dumps(( + return self.user_id + " " + _json_encoder.encode(( self.access_token, self.ip, self.user_agent, self.device_id, self.last_seen, )) diff --git a/synapse/rest/client/v1/room.py b/synapse/rest/client/v1/room.py index f8999d64d7..70d788deea 100644 --- a/synapse/rest/client/v1/room.py +++ b/synapse/rest/client/v1/room.py @@ -30,7 +30,7 @@ from synapse.http.servlet import ( import logging import urllib -import ujson as json +import simplejson as json logger = logging.getLogger(__name__) diff --git a/synapse/rest/client/v2_alpha/sync.py b/synapse/rest/client/v2_alpha/sync.py index a0a8e4b8e4..eb91c0b293 100644 --- a/synapse/rest/client/v2_alpha/sync.py +++ b/synapse/rest/client/v2_alpha/sync.py @@ -33,7 +33,7 @@ from ._base import set_timeline_upper_limit import itertools import logging -import ujson as json +import simplejson as json logger = logging.getLogger(__name__) diff --git a/synapse/rest/media/v1/preview_url_resource.py b/synapse/rest/media/v1/preview_url_resource.py index 31fe7aa75c..0fc21540c6 100644 --- a/synapse/rest/media/v1/preview_url_resource.py +++ b/synapse/rest/media/v1/preview_url_resource.py @@ -23,7 +23,7 @@ import re import shutil import sys import traceback -import ujson as json +import simplejson as json import urlparse from twisted.web.server import NOT_DONE_YET diff --git a/synapse/state.py b/synapse/state.py index 932f602508..26093c8434 100644 --- a/synapse/state.py +++ b/synapse/state.py @@ -132,7 +132,7 @@ class StateHandler(object): state_map = yield self.store.get_events(state.values(), get_prev_content=False) state = { - key: state_map[e_id] for key, e_id in state.items() if e_id in state_map + key: state_map[e_id] for key, e_id in state.iteritems() if e_id in state_map } defer.returnValue(state) @@ -378,7 +378,7 @@ class StateHandler(object): new_state = resolve_events_with_state_map(state_set_ids, state_map) new_state = { - key: state_map[ev_id] for key, ev_id in new_state.items() + key: state_map[ev_id] for key, ev_id in new_state.iteritems() } return new_state @@ -458,15 +458,15 @@ class StateResolutionHandler(object): # build a map from state key to the event_ids which set that state. # dict[(str, str), set[str]) state = {} - for st in state_groups_ids.values(): - for key, e_id in st.items(): + for st in state_groups_ids.itervalues(): + for key, e_id in st.iteritems(): state.setdefault(key, set()).add(e_id) # build a map from state key to the event_ids which set that state, # including only those where there are state keys in conflict. conflicted_state = { k: list(v) - for k, v in state.items() + for k, v in state.iteritems() if len(v) > 1 } @@ -480,36 +480,37 @@ class StateResolutionHandler(object): ) else: new_state = { - key: e_ids.pop() for key, e_ids in state.items() + key: e_ids.pop() for key, e_ids in state.iteritems() } - # if the new state matches any of the input state groups, we can - # use that state group again. Otherwise we will generate a state_id - # which will be used as a cache key for future resolutions, but - # not get persisted. - state_group = None - new_state_event_ids = frozenset(new_state.values()) - for sg, events in state_groups_ids.items(): - if new_state_event_ids == frozenset(e_id for e_id in events): - state_group = sg - break - - # TODO: We want to create a state group for this set of events, to - # increase cache hits, but we need to make sure that it doesn't - # end up as a prev_group without being added to the database - - prev_group = None - delta_ids = None - for old_group, old_ids in state_groups_ids.iteritems(): - if not set(new_state) - set(old_ids): - n_delta_ids = { - k: v - for k, v in new_state.iteritems() - if old_ids.get(k) != v - } - if not delta_ids or len(n_delta_ids) < len(delta_ids): - prev_group = old_group - delta_ids = n_delta_ids + with Measure(self.clock, "state.create_group_ids"): + # if the new state matches any of the input state groups, we can + # use that state group again. Otherwise we will generate a state_id + # which will be used as a cache key for future resolutions, but + # not get persisted. + state_group = None + new_state_event_ids = frozenset(new_state.itervalues()) + for sg, events in state_groups_ids.iteritems(): + if new_state_event_ids == frozenset(e_id for e_id in events): + state_group = sg + break + + # TODO: We want to create a state group for this set of events, to + # increase cache hits, but we need to make sure that it doesn't + # end up as a prev_group without being added to the database + + prev_group = None + delta_ids = None + for old_group, old_ids in state_groups_ids.iteritems(): + if not set(new_state) - set(old_ids): + n_delta_ids = { + k: v + for k, v in new_state.iteritems() + if old_ids.get(k) != v + } + if not delta_ids or len(n_delta_ids) < len(delta_ids): + prev_group = old_group + delta_ids = n_delta_ids cache = _StateCacheEntry( state=new_state, @@ -702,7 +703,7 @@ def _resolve_with_state(unconflicted_state_ids, conflicted_state_ds, auth_event_ auth_events = { key: state_map[ev_id] - for key, ev_id in auth_event_ids.items() + for key, ev_id in auth_event_ids.iteritems() if ev_id in state_map } @@ -740,7 +741,7 @@ def _resolve_state_events(conflicted_state, auth_events): auth_events.update(resolved_state) - for key, events in conflicted_state.items(): + for key, events in conflicted_state.iteritems(): if key[0] == EventTypes.JoinRules: logger.debug("Resolving conflicted join rules %r", events) resolved_state[key] = _resolve_auth_events( @@ -750,7 +751,7 @@ def _resolve_state_events(conflicted_state, auth_events): auth_events.update(resolved_state) - for key, events in conflicted_state.items(): + for key, events in conflicted_state.iteritems(): if key[0] == EventTypes.Member: logger.debug("Resolving conflicted member lists %r", events) resolved_state[key] = _resolve_auth_events( @@ -760,7 +761,7 @@ def _resolve_state_events(conflicted_state, auth_events): auth_events.update(resolved_state) - for key, events in conflicted_state.items(): + for key, events in conflicted_state.iteritems(): if key not in resolved_state: logger.debug("Resolving conflicted state %r:%r", key, events) resolved_state[key] = _resolve_normal_events( diff --git a/synapse/storage/account_data.py b/synapse/storage/account_data.py index e70c9423e3..f83ff0454a 100644 --- a/synapse/storage/account_data.py +++ b/synapse/storage/account_data.py @@ -23,7 +23,7 @@ from synapse.util.caches.stream_change_cache import StreamChangeCache from synapse.util.caches.descriptors import cached, cachedList, cachedInlineCallbacks import abc -import ujson as json +import simplejson as json import logging logger = logging.getLogger(__name__) diff --git a/synapse/storage/background_updates.py b/synapse/storage/background_updates.py index c88759bf2c..8af325a9f5 100644 --- a/synapse/storage/background_updates.py +++ b/synapse/storage/background_updates.py @@ -19,7 +19,7 @@ from . import engines from twisted.internet import defer -import ujson as json +import simplejson as json import logging logger = logging.getLogger(__name__) diff --git a/synapse/storage/deviceinbox.py b/synapse/storage/deviceinbox.py index 548e795daf..a879e5bfc1 100644 --- a/synapse/storage/deviceinbox.py +++ b/synapse/storage/deviceinbox.py @@ -14,7 +14,7 @@ # limitations under the License. import logging -import ujson +import simplejson from twisted.internet import defer @@ -85,7 +85,7 @@ class DeviceInboxStore(BackgroundUpdateStore): ) rows = [] for destination, edu in remote_messages_by_destination.items(): - edu_json = ujson.dumps(edu) + edu_json = simplejson.dumps(edu) rows.append((destination, stream_id, now_ms, edu_json)) txn.executemany(sql, rows) @@ -177,7 +177,7 @@ class DeviceInboxStore(BackgroundUpdateStore): " WHERE user_id = ?" ) txn.execute(sql, (user_id,)) - message_json = ujson.dumps(messages_by_device["*"]) + message_json = simplejson.dumps(messages_by_device["*"]) for row in txn: # Add the message for all devices for this user on this # server. @@ -199,7 +199,7 @@ class DeviceInboxStore(BackgroundUpdateStore): # Only insert into the local inbox if the device exists on # this server device = row[0] - message_json = ujson.dumps(messages_by_device[device]) + message_json = simplejson.dumps(messages_by_device[device]) messages_json_for_user[device] = message_json if messages_json_for_user: @@ -253,7 +253,7 @@ class DeviceInboxStore(BackgroundUpdateStore): messages = [] for row in txn: stream_pos = row[0] - messages.append(ujson.loads(row[1])) + messages.append(simplejson.loads(row[1])) if len(messages) < limit: stream_pos = current_stream_id return (messages, stream_pos) @@ -389,7 +389,7 @@ class DeviceInboxStore(BackgroundUpdateStore): messages = [] for row in txn: stream_pos = row[0] - messages.append(ujson.loads(row[1])) + messages.append(simplejson.loads(row[1])) if len(messages) < limit: stream_pos = current_stream_id return (messages, stream_pos) diff --git a/synapse/storage/devices.py b/synapse/storage/devices.py index bd2effdf34..712106b83a 100644 --- a/synapse/storage/devices.py +++ b/synapse/storage/devices.py @@ -13,7 +13,7 @@ # See the License for the specific language governing permissions and # limitations under the License. import logging -import ujson as json +import simplejson as json from twisted.internet import defer diff --git a/synapse/storage/end_to_end_keys.py b/synapse/storage/end_to_end_keys.py index 2cebb203c6..ff8538ddf8 100644 --- a/synapse/storage/end_to_end_keys.py +++ b/synapse/storage/end_to_end_keys.py @@ -17,7 +17,7 @@ from twisted.internet import defer from synapse.util.caches.descriptors import cached from canonicaljson import encode_canonical_json -import ujson as json +import simplejson as json from ._base import SQLBaseStore diff --git a/synapse/storage/event_push_actions.py b/synapse/storage/event_push_actions.py index 01f8339825..e78f8d0114 100644 --- a/synapse/storage/event_push_actions.py +++ b/synapse/storage/event_push_actions.py @@ -22,7 +22,7 @@ from synapse.types import RoomStreamToken from .stream import lower_bound import logging -import ujson as json +import simplejson as json logger = logging.getLogger(__name__) diff --git a/synapse/storage/events.py b/synapse/storage/events.py index 3890878170..ece5e6c41f 100644 --- a/synapse/storage/events.py +++ b/synapse/storage/events.py @@ -14,15 +14,19 @@ # See the License for the specific language governing permissions and # limitations under the License. -from synapse.storage.events_worker import EventsWorkerStore +from collections import OrderedDict, deque, namedtuple +from functools import wraps +import logging +import simplejson as json from twisted.internet import defer -from synapse.events import USE_FROZEN_DICTS +from synapse.storage.events_worker import EventsWorkerStore from synapse.util.async import ObservableDeferred +from synapse.util.frozenutils import frozendict_json_encoder from synapse.util.logcontext import ( - PreserveLoggingContext, make_deferred_yieldable + PreserveLoggingContext, make_deferred_yieldable, ) from synapse.util.logutils import log_function from synapse.util.metrics import Measure @@ -30,16 +34,8 @@ from synapse.api.constants import EventTypes from synapse.api.errors import SynapseError from synapse.util.caches.descriptors import cached, cachedInlineCallbacks from synapse.types import get_domain_from_id - -from canonicaljson import encode_canonical_json -from collections import deque, namedtuple, OrderedDict -from functools import wraps - import synapse.metrics -import logging -import ujson as json - # these are only included to make the type annotations work from synapse.events import EventBase # noqa: F401 from synapse.events.snapshot import EventContext # noqa: F401 @@ -53,13 +49,25 @@ event_counter = metrics.register_counter( "persisted_events_sep", labels=["type", "origin_type", "origin_entity"] ) +# The number of times we are recalculating the current state +state_delta_counter = metrics.register_counter( + "state_delta", +) +# The number of times we are recalculating state when there is only a +# single forward extremity +state_delta_single_event_counter = metrics.register_counter( + "state_delta_single_event", +) +# The number of times we are reculating state when we could have resonably +# calculated the delta when we calculated the state for an event we were +# persisting. +state_delta_reuse_delta_counter = metrics.register_counter( + "state_delta_reuse_delta", +) + def encode_json(json_object): - if USE_FROZEN_DICTS: - # ujson doesn't like frozen_dicts - return encode_canonical_json(json_object) - else: - return json.dumps(json_object, ensure_ascii=False) + return frozendict_json_encoder.encode(json_object) class _EventPeristenceQueue(object): @@ -369,7 +377,8 @@ class EventsStore(EventsWorkerStore): room_id, ev_ctx_rm, latest_event_ids ) - if new_latest_event_ids == set(latest_event_ids): + latest_event_ids = set(latest_event_ids) + if new_latest_event_ids == latest_event_ids: # No change in extremities, so no change in state continue @@ -390,6 +399,26 @@ class EventsStore(EventsWorkerStore): if all_single_prev_not_state: continue + state_delta_counter.inc() + if len(new_latest_event_ids) == 1: + state_delta_single_event_counter.inc() + + # This is a fairly handwavey check to see if we could + # have guessed what the delta would have been when + # processing one of these events. + # What we're interested in is if the latest extremities + # were the same when we created the event as they are + # now. When this server creates a new event (as opposed + # to receiving it over federation) it will use the + # forward extremities as the prev_events, so we can + # guess this by looking at the prev_events and checking + # if they match the current forward extremities. + for ev, _ in ev_ctx_rm: + prev_event_ids = set(e for e, _ in ev.prev_events) + if latest_event_ids == prev_event_ids: + state_delta_reuse_delta_counter.inc() + break + logger.info( "Calculating state delta for room %s", room_id, ) diff --git a/synapse/storage/events_worker.py b/synapse/storage/events_worker.py index 86c3b48ad4..2e23dd78ba 100644 --- a/synapse/storage/events_worker.py +++ b/synapse/storage/events_worker.py @@ -28,7 +28,7 @@ from synapse.api.errors import SynapseError from collections import namedtuple import logging -import ujson as json +import simplejson as json # these are only included to make the type annotations work from synapse.events import EventBase # noqa: F401 diff --git a/synapse/storage/group_server.py b/synapse/storage/group_server.py index 8fde1aab8e..d03858234b 100644 --- a/synapse/storage/group_server.py +++ b/synapse/storage/group_server.py @@ -19,7 +19,7 @@ from synapse.api.errors import SynapseError from ._base import SQLBaseStore -import ujson as json +import simplejson as json # The category ID for the "default" category. We don't store as null in the diff --git a/synapse/storage/receipts.py b/synapse/storage/receipts.py index eac8694e0f..63997ed449 100644 --- a/synapse/storage/receipts.py +++ b/synapse/storage/receipts.py @@ -23,7 +23,7 @@ from twisted.internet import defer import abc import logging -import ujson as json +import simplejson as json logger = logging.getLogger(__name__) diff --git a/synapse/storage/registration.py b/synapse/storage/registration.py index d809b2ba46..6b557ca0cf 100644 --- a/synapse/storage/registration.py +++ b/synapse/storage/registration.py @@ -460,14 +460,12 @@ class RegistrationStore(RegistrationWorkerStore, """ def _find_next_generated_user_id(txn): txn.execute("SELECT name FROM users") - rows = self.cursor_to_dict(txn) regex = re.compile("^@(\d+):") found = set() - for r in rows: - user_id = r["name"] + for user_id, in txn: match = regex.search(user_id) if match: found.add(int(match.group(1))) diff --git a/synapse/storage/room.py b/synapse/storage/room.py index 34ed84ea22..908551d6d9 100644 --- a/synapse/storage/room.py +++ b/synapse/storage/room.py @@ -22,7 +22,7 @@ from synapse.util.caches.descriptors import cached, cachedInlineCallbacks import collections import logging -import ujson as json +import simplejson as json import re logger = logging.getLogger(__name__) diff --git a/synapse/storage/roommember.py b/synapse/storage/roommember.py index 52e19e16b0..d662d1cfc0 100644 --- a/synapse/storage/roommember.py +++ b/synapse/storage/roommember.py @@ -28,7 +28,7 @@ from synapse.api.constants import Membership, EventTypes from synapse.types import get_domain_from_id import logging -import ujson as json +import simplejson as json logger = logging.getLogger(__name__) diff --git a/synapse/storage/schema/delta/14/upgrade_appservice_db.py b/synapse/storage/schema/delta/14/upgrade_appservice_db.py index 8755bb2e49..4d725b92fe 100644 --- a/synapse/storage/schema/delta/14/upgrade_appservice_db.py +++ b/synapse/storage/schema/delta/14/upgrade_appservice_db.py @@ -12,9 +12,10 @@ # See the License for the specific language governing permissions and # limitations under the License. -import json import logging +import simplejson as json + logger = logging.getLogger(__name__) diff --git a/synapse/storage/schema/delta/25/fts.py b/synapse/storage/schema/delta/25/fts.py index 4269ac69ad..e7351c3ae6 100644 --- a/synapse/storage/schema/delta/25/fts.py +++ b/synapse/storage/schema/delta/25/fts.py @@ -17,7 +17,7 @@ import logging from synapse.storage.prepare_database import get_statements from synapse.storage.engines import PostgresEngine, Sqlite3Engine -import ujson +import simplejson logger = logging.getLogger(__name__) @@ -66,7 +66,7 @@ def run_create(cur, database_engine, *args, **kwargs): "max_stream_id_exclusive": max_stream_id + 1, "rows_inserted": 0, } - progress_json = ujson.dumps(progress) + progress_json = simplejson.dumps(progress) sql = ( "INSERT into background_updates (update_name, progress_json)" diff --git a/synapse/storage/schema/delta/27/ts.py b/synapse/storage/schema/delta/27/ts.py index 71b12a2731..6df57b5206 100644 --- a/synapse/storage/schema/delta/27/ts.py +++ b/synapse/storage/schema/delta/27/ts.py @@ -16,7 +16,7 @@ import logging from synapse.storage.prepare_database import get_statements -import ujson +import simplejson logger = logging.getLogger(__name__) @@ -45,7 +45,7 @@ def run_create(cur, database_engine, *args, **kwargs): "max_stream_id_exclusive": max_stream_id + 1, "rows_inserted": 0, } - progress_json = ujson.dumps(progress) + progress_json = simplejson.dumps(progress) sql = ( "INSERT into background_updates (update_name, progress_json)" diff --git a/synapse/storage/schema/delta/31/search_update.py b/synapse/storage/schema/delta/31/search_update.py index 470ae0c005..fe6b7d196d 100644 --- a/synapse/storage/schema/delta/31/search_update.py +++ b/synapse/storage/schema/delta/31/search_update.py @@ -16,7 +16,7 @@ from synapse.storage.engines import PostgresEngine from synapse.storage.prepare_database import get_statements import logging -import ujson +import simplejson logger = logging.getLogger(__name__) @@ -49,7 +49,7 @@ def run_create(cur, database_engine, *args, **kwargs): "rows_inserted": 0, "have_added_indexes": False, } - progress_json = ujson.dumps(progress) + progress_json = simplejson.dumps(progress) sql = ( "INSERT into background_updates (update_name, progress_json)" diff --git a/synapse/storage/schema/delta/33/event_fields.py b/synapse/storage/schema/delta/33/event_fields.py index 83066cccc9..1e002f9db2 100644 --- a/synapse/storage/schema/delta/33/event_fields.py +++ b/synapse/storage/schema/delta/33/event_fields.py @@ -15,7 +15,7 @@ from synapse.storage.prepare_database import get_statements import logging -import ujson +import simplejson logger = logging.getLogger(__name__) @@ -44,7 +44,7 @@ def run_create(cur, database_engine, *args, **kwargs): "max_stream_id_exclusive": max_stream_id + 1, "rows_inserted": 0, } - progress_json = ujson.dumps(progress) + progress_json = simplejson.dumps(progress) sql = ( "INSERT into background_updates (update_name, progress_json)" diff --git a/synapse/storage/search.py b/synapse/storage/search.py index 2755acff40..984643b057 100644 --- a/synapse/storage/search.py +++ b/synapse/storage/search.py @@ -16,7 +16,7 @@ from collections import namedtuple import logging import re -import ujson as json +import simplejson as json from twisted.internet import defer diff --git a/synapse/storage/tags.py b/synapse/storage/tags.py index fc46bf7bb3..13bff9f055 100644 --- a/synapse/storage/tags.py +++ b/synapse/storage/tags.py @@ -19,7 +19,7 @@ from synapse.storage.account_data import AccountDataWorkerStore from synapse.util.caches.descriptors import cached from twisted.internet import defer -import ujson as json +import simplejson as json import logging logger = logging.getLogger(__name__) diff --git a/synapse/storage/transactions.py b/synapse/storage/transactions.py index 8f61f7ffae..f825264ea9 100644 --- a/synapse/storage/transactions.py +++ b/synapse/storage/transactions.py @@ -23,7 +23,7 @@ from canonicaljson import encode_canonical_json from collections import namedtuple import logging -import ujson as json +import simplejson as json logger = logging.getLogger(__name__) diff --git a/synapse/storage/user_directory.py b/synapse/storage/user_directory.py index dfdcbb3181..d6e289ffbe 100644 --- a/synapse/storage/user_directory.py +++ b/synapse/storage/user_directory.py @@ -667,7 +667,7 @@ class UserDirectoryStore(SQLBaseStore): # The array of numbers are the weights for the various part of the # search: (domain, _, display name, localpart) sql = """ - SELECT d.user_id, display_name, avatar_url + SELECT d.user_id AS user_id, display_name, avatar_url FROM user_directory_search INNER JOIN user_directory AS d USING (user_id) %s @@ -702,7 +702,7 @@ class UserDirectoryStore(SQLBaseStore): search_query = _parse_query_sqlite(search_term) sql = """ - SELECT d.user_id, display_name, avatar_url + SELECT d.user_id AS user_id, display_name, avatar_url FROM user_directory_search INNER JOIN user_directory AS d USING (user_id) %s diff --git a/synapse/types.py b/synapse/types.py index 7cb24cecb2..f1f41ccf90 100644 --- a/synapse/types.py +++ b/synapse/types.py @@ -12,11 +12,11 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. -import string from synapse.api.errors import SynapseError from collections import namedtuple +import re class Requester(namedtuple("Requester", [ @@ -214,7 +214,8 @@ class GroupID(DomainSpecificString): return group_id -mxid_localpart_allowed_characters = set("_-./=" + string.ascii_lowercase + string.digits) +# A regex that matches any valid mxid characters +MXID_LOCALPART_REGEX = re.compile("^[_\-./=a-z0-9]*$") def contains_invalid_mxid_characters(localpart): @@ -226,7 +227,7 @@ def contains_invalid_mxid_characters(localpart): Returns: bool: True if there are any naughty characters """ - return any(c not in mxid_localpart_allowed_characters for c in localpart) + return not MXID_LOCALPART_REGEX.match(localpart) class StreamToken( diff --git a/synapse/util/caches/dictionary_cache.py b/synapse/util/caches/dictionary_cache.py index d4105822b3..1709e8b429 100644 --- a/synapse/util/caches/dictionary_cache.py +++ b/synapse/util/caches/dictionary_cache.py @@ -132,9 +132,13 @@ class DictionaryCache(object): self._update_or_insert(key, value, known_absent) def _update_or_insert(self, key, value, known_absent): - entry = self.cache.setdefault(key, DictionaryEntry(False, set(), {})) + # We pop and reinsert as we need to tell the cache the size may have + # changed + + entry = self.cache.pop(key, DictionaryEntry(False, set(), {})) entry.value.update(value) entry.known_absent.update(known_absent) + self.cache[key] = entry def _insert(self, key, value, known_absent): self.cache[key] = DictionaryEntry(True, known_absent, value) diff --git a/synapse/util/caches/lrucache.py b/synapse/util/caches/lrucache.py index f088dd430e..1c5a982094 100644 --- a/synapse/util/caches/lrucache.py +++ b/synapse/util/caches/lrucache.py @@ -154,14 +154,21 @@ class LruCache(object): def cache_set(key, value, callbacks=[]): node = cache.get(key, None) if node is not None: - if value != node.value: + # We sometimes store large objects, e.g. dicts, which cause + # the inequality check to take a long time. So let's only do + # the check if we have some callbacks to call. + if node.callbacks and value != node.value: for cb in node.callbacks: cb() node.callbacks.clear() - if size_callback: - cached_cache_len[0] -= size_callback(node.value) - cached_cache_len[0] += size_callback(value) + # We don't bother to protect this by value != node.value as + # generally size_callback will be cheap compared with equality + # checks. (For example, taking the size of two dicts is quicker + # than comparing them for equality.) + if size_callback: + cached_cache_len[0] -= size_callback(node.value) + cached_cache_len[0] += size_callback(value) node.callbacks.update(callbacks) diff --git a/synapse/util/frozenutils.py b/synapse/util/frozenutils.py index 6322f0f55c..f497b51f4a 100644 --- a/synapse/util/frozenutils.py +++ b/synapse/util/frozenutils.py @@ -14,6 +14,7 @@ # limitations under the License. from frozendict import frozendict +import simplejson as json def freeze(o): @@ -49,3 +50,21 @@ def unfreeze(o): pass return o + + +def _handle_frozendict(obj): + """Helper for EventEncoder. Makes frozendicts serializable by returning + the underlying dict + """ + if type(obj) is frozendict: + # fishing the protected dict out of the object is a bit nasty, + # but we don't really want the overhead of copying the dict. + return obj._dict + raise TypeError('Object of type %s is not JSON serializable' % + obj.__class__.__name__) + + +# A JSONEncoder which is capable of encoding frozendics without barfing +frozendict_json_encoder = json.JSONEncoder( + default=_handle_frozendict, +) diff --git a/synapse/util/httpresourcetree.py b/synapse/util/httpresourcetree.py index 45be47159a..d747849553 100644 --- a/synapse/util/httpresourcetree.py +++ b/synapse/util/httpresourcetree.py @@ -12,7 +12,7 @@ # See the License for the specific language governing permissions and # limitations under the License. -from twisted.web.resource import Resource +from twisted.web.resource import NoResource import logging @@ -45,7 +45,7 @@ def create_resource_tree(desired_tree, root_resource): for path_seg in full_path.split('/')[1:-1]: if path_seg not in last_resource.listNames(): # resource doesn't exist, so make a "dummy resource" - child_resource = Resource() + child_resource = NoResource() last_resource.putChild(path_seg, child_resource) res_id = _resource_id(last_resource, path_seg) resource_mappings[res_id] = child_resource |