Refactor store.have_events

It turns out that most of the time we were calling have_events, we were only
using half of the result. Replace have_events with have_seen_events and
get_rejection_reasons, so that we can see what's going on a bit more clearly.

synapse/storage/events.py

@@ -16,6 +16,7 @@
 
 from collections import OrderedDict, deque, namedtuple
 from functools import wraps
+import itertools
 import logging
 
 import simplejson as json
@@ -1320,13 +1321,49 @@ class EventsStore(EventsWorkerStore):
 
         defer.returnValue(set(r["event_id"] for r in rows))
 
-    def have_events(self, event_ids):
+    @defer.inlineCallbacks
+    def have_seen_events(self, event_ids):
         """Given a list of event ids, check if we have already processed them.
 
+        Args:
+            event_ids (iterable[str]):
+
         Returns:
-            dict: Has an entry for each event id we already have seen. Maps to
-            the rejected reason string if we rejected the event, else maps to
-            None.
+            Deferred[set[str]]: The events we have already seen.
+        """
+        results = set()
+
+        def have_seen_events_txn(txn, chunk):
+            sql = (
+                "SELECT event_id FROM events as e WHERE e.event_id IN (%s)"
+                % (",".join("?" * len(chunk)), )
+            )
+            txn.execute(sql, chunk)
+            for (event_id, ) in txn:
+                results.add(event_id)
+
+        # break the input up into chunks of 100
+        input_iterator = iter(event_ids)
+        for chunk in iter(lambda: list(itertools.islice(input_iterator, 100)),
+                          []):
+            yield self.runInteraction(
+                "have_seen_events",
+                have_seen_events_txn,
+                chunk,
+            )
+        defer.returnValue(results)
+
+    def get_seen_events_with_rejections(self, event_ids):
+        """Given a list of event ids, check if we rejected them.
+
+        Args:
+            event_ids (list[str])
+
+        Returns:
+            Deferred[dict[str, str|None):
+                Has an entry for each event id we already have seen. Maps to
+                the rejected reason string if we rejected the event, else maps
+                to None.
         """
         if not event_ids:
             return defer.succeed({})
@@ -1348,9 +1385,7 @@ class EventsStore(EventsWorkerStore):
 
             return res
 
-        return self.runInteraction(
-            "have_events", f,
-        )
+        return self.runInteraction("get_rejection_reasons", f)
 
     @defer.inlineCallbacks
     def count_daily_messages(self):