Fix perf regression in PR #3530

The get_entities_changed function was changed to return all changed
entities since the given stream position, rather than only those changed
from a given list of entities. This resulted in the function incorrectly
returning large numbers of entities that, for example, caused large
increases in database usage.

1 files changed, 6 insertions, 1 deletions

diff --git a/synapse/util/caches/stream_change_cache.py b/synapse/util/caches/stream_change_cache.py
index 258655349b..c1e76b1a0e 100644
--- a/synapse/util/caches/stream_change_cache.py
+++ b/synapse/util/caches/stream_change_cache.py
@@ -74,12 +74,17 @@ class StreamChangeCache(object):
         assert type(stream_pos) is int
 
         if stream_pos >= self._earliest_known_stream_pos:
-            result = {
+            changed_entities = {
                 self._cache[k] for k in self._cache.islice(
                     start=self._cache.bisect_right(stream_pos),
                 )
             }
 
+            result = {
+                e for e in entities
+                if e in changed_entities
+            }
+
             self.metrics.inc_hits()
         else:
             result = set(entities)