Make get_state_groups_from_groups faster.

Most of the time was spent copying a dict to filter out sentinel values
that indicated that keys did not exist in the dict. The sentinel values
were added to ensure that we cached the non-existence of keys.

By updating DictionaryCache to keep track of which keys were known to
not exist itself we can remove a dictionary copy.

1 files changed, 46 insertions, 11 deletions

diff --git a/synapse/util/caches/dictionary_cache.py b/synapse/util/caches/dictionary_cache.py
index cb6933c61c..d4105822b3 100644
--- a/synapse/util/caches/dictionary_cache.py
+++ b/synapse/util/caches/dictionary_cache.py
@@ -23,7 +23,17 @@ import logging
 logger = logging.getLogger(__name__)
 
 
-class DictionaryEntry(namedtuple("DictionaryEntry", ("full", "value"))):
+class DictionaryEntry(namedtuple("DictionaryEntry", ("full", "known_absent", "value"))):
+    """Returned when getting an entry from the cache
+
+    Attributes:
+        full (bool): Whether the cache has the full or dict or just some keys.
+            If not full then not all requested keys will necessarily be present
+            in `value`
+        known_absent (set): Keys that were looked up in the dict and were not
+            there.
+        value (dict): The full or partial dict value
+    """
     def __len__(self):
         return len(self.value)
 
@@ -58,21 +68,31 @@ class DictionaryCache(object):
                 )
 
     def get(self, key, dict_keys=None):
+        """Fetch an entry out of the cache
+
+        Args:
+            key
+            dict_key(list): If given a set of keys then return only those keys
+                that exist in the cache.
+
+        Returns:
+            DictionaryEntry
+        """
         entry = self.cache.get(key, self.sentinel)
         if entry is not self.sentinel:
             self.metrics.inc_hits()
 
             if dict_keys is None:
-                return DictionaryEntry(entry.full, dict(entry.value))
+                return DictionaryEntry(entry.full, entry.known_absent, dict(entry.value))
             else:
-                return DictionaryEntry(entry.full, {
+                return DictionaryEntry(entry.full, entry.known_absent, {
                     k: entry.value[k]
                     for k in dict_keys
                     if k in entry.value
                 })
 
         self.metrics.inc_misses()
-        return DictionaryEntry(False, {})
+        return DictionaryEntry(False, set(), {})
 
     def invalidate(self, key):
         self.check_thread()
@@ -87,19 +107,34 @@ class DictionaryCache(object):
         self.sequence += 1
         self.cache.clear()
 
-    def update(self, sequence, key, value, full=False):
+    def update(self, sequence, key, value, full=False, known_absent=None):
+        """Updates the entry in the cache
+
+        Args:
+            sequence
+            key
+            value (dict): The value to update the cache with.
+            full (bool): Whether the given value is the full dict, or just a
+                partial subset there of. If not full then any existing entries
+                for the key will be updated.
+            known_absent (set): Set of keys that we know don't exist in the full
+                dict.
+        """
         self.check_thread()
         if self.sequence == sequence:
             # Only update the cache if the caches sequence number matches the
             # number that the cache had before the SELECT was started (SYN-369)
+            if known_absent is None:
+                known_absent = set()
             if full:
-                self._insert(key, value)
+                self._insert(key, value, known_absent)
             else:
-                self._update_or_insert(key, value)
+                self._update_or_insert(key, value, known_absent)
 
-    def _update_or_insert(self, key, value):
-        entry = self.cache.setdefault(key, DictionaryEntry(False, {}))
+    def _update_or_insert(self, key, value, known_absent):
+        entry = self.cache.setdefault(key, DictionaryEntry(False, set(), {}))
         entry.value.update(value)
+        entry.known_absent.update(known_absent)
 
-    def _insert(self, key, value):
-        self.cache[key] = DictionaryEntry(True, value)
+    def _insert(self, key, value, known_absent):
+        self.cache[key] = DictionaryEntry(True, known_absent, value)