Merge tag 'v1.32.2' into babolivier/dinsic_1.41.0

Synapse 1.32.2 (2021-04-22)
===========================

This release includes a fix for a regression introduced in 1.32.0.

Bugfixes
--------

- Fix a regression in Synapse 1.32.0 and 1.32.1 which caused `LoggingContext` errors in plugins. ([\#9857](matrix-org/synapse#9857))

Author: babolivier

CHANGES.md

@@ -1,12 +1,58 @@
+Synapse 1.32.2 (2021-04-22)
+===========================
+
+This release includes a fix for a regression introduced in 1.32.0.
+
+Bugfixes
+--------
+
+- Fix a regression in Synapse 1.32.0 and 1.32.1 which caused `LoggingContext` errors in plugins. ([\#9857](https://github.com/matrix-org/synapse/issues/9857))
+
+
+Synapse 1.32.1 (2021-04-21)
+===========================
+
+This release fixes [a regression](https://github.com/matrix-org/synapse/issues/9853)
+in Synapse 1.32.0 that caused connected Prometheus instances to become unstable. 
+
+However, as this release is still subject to the `LoggingContext` change in 1.32.0,
+it is recommended to remain on or downgrade to 1.31.0.
+
+Bugfixes
+--------
+
+- Fix a regression in Synapse 1.32.0 which caused Synapse to report large numbers of Prometheus time series, potentially overwhelming Prometheus instances. ([\#9854](https://github.com/matrix-org/synapse/issues/9854))
+
+
 Synapse 1.32.0 (2021-04-20)
 ===========================
 
+**Note:** This release introduces [a regression](https://github.com/matrix-org/synapse/issues/9853)
+that can overwhelm connected Prometheus instances. This issue was not present in
+1.32.0rc1. If affected, it is recommended to downgrade to 1.31.0 in the meantime, and 
+follow [these instructions](https://github.com/matrix-org/synapse/pull/9854#issuecomment-823472183)
+to clean up any excess writeahead logs.
+
+**Note:** This release also mistakenly included a change that may affected Synapse 
+modules that import `synapse.logging.context.LoggingContext`, such as
+[synapse-s3-storage-provider](https://github.com/matrix-org/synapse-s3-storage-provider).
+This will be fixed in a later Synapse version.
+
 **Note:** This release requires Python 3.6+ and Postgres 9.6+ or SQLite 3.22+.
 
 This release removes the deprecated `GET /_synapse/admin/v1/users/<user_id>` admin API. Please use the [v2 API](https://github.com/matrix-org/synapse/blob/develop/docs/admin_api/user_admin_api.rst#query-user-account) instead, which has improved capabilities.
 
 This release requires Application Services to use type `m.login.application_service` when registering users via the `/_matrix/client/r0/register` endpoint to comply with the spec. Please ensure your Application Services are up to date.
 
+If you are using the `packages.matrix.org` Debian repository for Synapse packages, 
+note that we have recently updated the expiry date on the gpg signing key. If you see an 
+error similar to `The following signatures were invalid: EXPKEYSIG F473DD4473365DE1`, you
+will need to get a fresh copy of the keys. You can do so with:
+
+```sh
+sudo wget -O /usr/share/keyrings/matrix-org-archive-keyring.gpg https://packages.matrix.org/debian/matrix-org-archive-keyring.gpg
+```
+
 Bugfixes
 --------
 

UPGRADE.rst

@@ -88,6 +88,18 @@ for example:
 Upgrading to v1.32.0
 ====================
 
+Regression causing connected Prometheus instances to become overwhelmed
+-----------------------------------------------------------------------
+
+This release introduces `a regression <https://github.com/matrix-org/synapse/issues/9853>`_
+that can overwhelm connected Prometheus instances. This issue is not present in
+Synapse v1.32.0rc1.
+
+If you have been affected, please downgrade to 1.31.0. You then may need to
+remove excess writeahead logs in order for Prometheus to recover. Instructions
+for doing so are provided
+`here <https://github.com/matrix-org/synapse/pull/9854#issuecomment-823472183>`_.
+
 Dropping support for old Python, Postgres and SQLite versions
 -------------------------------------------------------------
 

debian/changelog

@@ -1,3 +1,15 @@
+matrix-synapse-py3 (1.32.2) stable; urgency=medium
+
+  * New synapse release 1.32.2.
+
+ -- Synapse Packaging team <[email protected]>  Wed, 22 Apr 2021 12:43:52 +0100
+
+matrix-synapse-py3 (1.32.1) stable; urgency=medium
+
+  * New synapse release 1.32.1.
+
+ -- Synapse Packaging team <[email protected]>  Wed, 21 Apr 2021 14:00:55 +0100
+
 matrix-synapse-py3 (1.32.0) stable; urgency=medium
 
   [ Dan Callahan ]

synapse/__init__.py

@@ -48,7 +48,7 @@
 except ImportError:
     pass
 
-__version__ = "1.32.0"
+__version__ = "1.32.2"
 
 if bool(os.environ.get("SYNAPSE_TEST_PATCH_LOG_CONTEXTS", False)):
     # We import here so that we don't have to install a bunch of deps when

synapse/logging/context.py

@@ -258,7 +258,8 @@ class LoggingContext:
           child to the parent
 
     Args:
-        name (str): Name for the context for debugging.
+        name: Name for the context for logging. If this is omitted, it is
+           inherited from the parent context.
         parent_context (LoggingContext|None): The parent of the new context
     """
 
@@ -277,12 +278,11 @@ class LoggingContext:
 
     def __init__(
         self,
-        name: str,
+        name: Optional[str] = None,
         parent_context: "Optional[LoggingContext]" = None,
         request: Optional[ContextRequest] = None,
     ) -> None:
         self.previous_context = current_context()
-        self.name = name
 
         # track the resources used by this context so far
         self._resource_usage = ContextResourceUsage()
@@ -314,6 +314,15 @@ def __init__(
             # the request param overrides the request from the parent context
             self.request = request
 
+        # if we don't have a `name`, but do have a parent context, use its name.
+        if self.parent_context and name is None:
+            name = str(self.parent_context)
+        if name is None:
+            raise ValueError(
+                "LoggingContext must be given either a name or a parent context"
+            )
+        self.name = name
+
     def __str__(self) -> str:
         return self.name
 

synapse/metrics/background_process_metrics.py

@@ -16,7 +16,7 @@
 import logging
 import threading
 from functools import wraps
-from typing import TYPE_CHECKING, Dict, Optional, Set
+from typing import TYPE_CHECKING, Dict, Optional, Set, Union
 
 from prometheus_client.core import REGISTRY, Counter, Gauge
 
@@ -199,7 +199,7 @@ async def run():
         _background_process_start_count.labels(desc).inc()
         _background_process_in_flight_count.labels(desc).inc()
 
-        with BackgroundProcessLoggingContext("%s-%s" % (desc, count)) as context:
+        with BackgroundProcessLoggingContext(desc, count) as context:
             try:
                 ctx = noop_context_manager()
                 if bg_start_span:
@@ -244,8 +244,20 @@ class BackgroundProcessLoggingContext(LoggingContext):
 
     __slots__ = ["_proc"]
 
-    def __init__(self, name: str):
-        super().__init__(name)
+    def __init__(self, name: str, instance_id: Optional[Union[int, str]] = None):
+        """
+
+        Args:
+            name: The name of the background process. Each distinct `name` gets a
+                separate prometheus time series.
+
+            instance_id: an identifer to add to `name` to distinguish this instance of
+                the named background process in the logs. If this is `None`, one is
+                made up based on id(self).
+        """
+        if instance_id is None:
+            instance_id = id(self)
+        super().__init__("%s-%s" % (name, instance_id))
         self._proc = _BackgroundProcess(name, self)
 
     def start(self, rusage: "Optional[resource._RUsage]"):

synapse/replication/tcp/protocol.py

@@ -185,7 +185,7 @@ def __init__(self, clock: Clock, handler: "ReplicationCommandHandler"):
         # a logcontext which we use for processing incoming commands. We declare it as a
         # background process so that the CPU stats get reported to prometheus.
         self._logging_context = BackgroundProcessLoggingContext(
-            "replication-conn-%s" % (self.conn_id,)
+            "replication-conn", self.conn_id
         )
 
     def connectionMade(self):