Fix bug where read-receipts lost their timestamps (#4927)

Make sure that they are sent correctly over the replication stream.

Fixes: #4898

3 files changed, 30 insertions, 12 deletions

diff --git a/synapse/replication/tcp/protocol.py b/synapse/replication/tcp/protocol.py
index 55630ba9a7..e16fad5261 100644
--- a/synapse/replication/tcp/protocol.py
+++ b/synapse/replication/tcp/protocol.py
@@ -223,14 +223,25 @@ class BaseReplicationStreamProtocol(LineOnlyReceiver):
             return
 
         # Now lets try and call on_<CMD_NAME> function
-        try:
-            run_as_background_process(
-                "replication-" + cmd.get_logcontext_id(),
-                getattr(self, "on_%s" % (cmd_name,)),
-                cmd,
-            )
-        except Exception:
-            logger.exception("[%s] Failed to handle line: %r", self.id(), line)
+        run_as_background_process(
+            "replication-" + cmd.get_logcontext_id(),
+            self.handle_command,
+            cmd,
+        )
+
+    def handle_command(self, cmd):
+        """Handle a command we have received over the replication stream.
+
+        By default delegates to on_<COMMAND>
+
+        Args:
+            cmd (synapse.replication.tcp.commands.Command): received command
+
+        Returns:
+            Deferred
+        """
+        handler = getattr(self, "on_%s" % (cmd.NAME,))
+        return handler(cmd)
 
     def close(self):
         logger.warn("[%s] Closing connection", self.id())
diff --git a/synapse/replication/tcp/streams.py b/synapse/replication/tcp/streams.py
index c1e626be3f..e23084baae 100644
--- a/synapse/replication/tcp/streams.py
+++ b/synapse/replication/tcp/streams.py
@@ -23,7 +23,7 @@ Each stream is defined by the following information:
     current_token:      The function that returns the current token for the stream
     update_function:    The function that returns a list of updates between two tokens
 """
-
+import itertools
 import logging
 from collections import namedtuple
 
@@ -195,8 +195,8 @@ class Stream(object):
                 limit=MAX_EVENTS_BEHIND + 1,
             )
 
-            if len(rows) >= MAX_EVENTS_BEHIND:
-                raise Exception("stream %s has fallen behind" % (self.NAME))
+            # never turn more than MAX_EVENTS_BEHIND + 1 into updates.
+            rows = itertools.islice(rows, MAX_EVENTS_BEHIND + 1)
         else:
             rows = yield self.update_function(
                 from_token, current_token,
@@ -204,6 +204,11 @@ class Stream(object):
 
         updates = [(row[0], self.ROW_TYPE(*row[1:])) for row in rows]
 
+        # check we didn't get more rows than the limit.
+        # doing it like this allows the update_function to be a generator.
+        if self._LIMITED and len(updates) >= MAX_EVENTS_BEHIND:
+            raise Exception("stream %s has fallen behind" % (self.NAME))
+
         defer.returnValue((updates, current_token))
 
     def current_token(self):
diff --git a/synapse/storage/receipts.py b/synapse/storage/receipts.py
index 0fd1ccc40a..89a1f7e3d7 100644
--- a/synapse/storage/receipts.py
+++ b/synapse/storage/receipts.py
@@ -301,7 +301,9 @@ class ReceiptsWorkerStore(SQLBaseStore):
                 args.append(limit)
             txn.execute(sql, args)
 
-            return txn.fetchall()
+            return (
+                r[0:5] + (json.loads(r[5]), ) for r in txn
+            )
         return self.runInteraction(
             "get_all_updated_receipts", get_all_updated_receipts_txn
         )