Merge branch 'erikj/fix_stalled_catchup' into matrix-org-hotfixes

2 files changed, 5 insertions, 2 deletions

diff --git a/changelog.d/9770.bugfix b/changelog.d/9770.bugfix
new file mode 100644

index 0000000000..baf93138de
--- /dev/null
+++ b/changelog.d/9770.bugfix
@@ -0,0 +1 @@
+Fix bug where sharded federation senders could get stuck repeatedly querying the DB in a loop, using lots of CPU.
diff --git a/synapse/federation/sender/__init__.py b/synapse/federation/sender/__init__.py

index 98bfce22ff..d821dcbf6a 100644
--- a/synapse/federation/sender/__init__.py
+++ b/synapse/federation/sender/__init__.py
@@ -734,16 +734,18 @@ class FederationSender(AbstractFederationSender):
                 self._catchup_after_startup_timer = None
                 break
 
+            last_processed = destinations_to_wake[-1]
+
             destinations_to_wake = [
                 d
                 for d in destinations_to_wake
                 if self._federation_shard_config.should_handle(self._instance_name, d)
             ]
 
-            for last_processed in destinations_to_wake:
+            for destination in destinations_to_wake:
                 logger.info(
                     "Destination %s has outstanding catch-up, waking up.",
                     last_processed,
                 )
-                self.wake_destination(last_processed)
+                self.wake_destination(destination)
                 await self.clock.sleep(CATCH_UP_STARTUP_INTERVAL_SEC)