Merge pull request #3005 from matrix-org/erikj/fix_cache_size

Fix bug where state cache used lots of memory

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)

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)