Merge pull request #3584 from matrix-org/erikj/use_cached

Only get cached state from context in persist_event

3 files changed, 21 insertions, 1 deletions

diff --git a/changelog.d/3584.misc b/changelog.d/3584.misc
new file mode 100644
index 0000000000..2374dc0c44
--- /dev/null
+++ b/changelog.d/3584.misc
@@ -0,0 +1 @@
+Lazily load state on master process when using workers to reduce DB consumption
diff --git a/synapse/events/snapshot.py b/synapse/events/snapshot.py
index a59064b416..189212b0fa 100644
--- a/synapse/events/snapshot.py
+++ b/synapse/events/snapshot.py
@@ -163,6 +163,9 @@ class EventContext(object):
         context._prev_state_id = input["prev_state_id"]
         context._event_type = input["event_type"]
         context._event_state_key = input["event_state_key"]
+
+        context._current_state_ids = None
+        context._prev_state_ids = None
         context._fetching_state_deferred = None
 
         context.state_group = input["state_group"]
@@ -214,6 +217,17 @@ class EventContext(object):
 
         defer.returnValue(self._prev_state_ids)
 
+    def get_cached_current_state_ids(self):
+        """Gets the current state IDs if we have them already cached.
+
+        Returns:
+            dict[(str, str), str]|None: Returns None if we haven't cached the
+            state or if state_group is None, which happens when the associated
+            event is an outlier.
+        """
+
+        return self._current_state_ids
+
     @defer.inlineCallbacks
     def _fill_out_state(self, store):
         """Called to populate the _current_state_ids and _prev_state_ids
diff --git a/synapse/storage/events.py b/synapse/storage/events.py
index bf4f3ee92a..c2910094d0 100644
--- a/synapse/storage/events.py
+++ b/synapse/storage/events.py
@@ -549,7 +549,12 @@ class EventsStore(EventsWorkerStore):
             if ctx.state_group in state_groups_map:
                 continue
 
-            state_groups_map[ctx.state_group] = yield ctx.get_current_state_ids(self)
+            # We're only interested in pulling out state that has already
+            # been cached in the context. We'll pull stuff out of the DB later
+            # if necessary.
+            current_state_ids = ctx.get_cached_current_state_ids()
+            if current_state_ids is not None:
+                state_groups_map[ctx.state_group] = current_state_ids
 
         # We need to map the event_ids to their state groups. First, let's
         # check if the event is one we're persisting, in which case we can