summary refs log tree commit diff
path: root/synapse
diff options
context:
space:
mode:
Diffstat (limited to 'synapse')
-rw-r--r--synapse/handlers/federation.py31
-rw-r--r--synapse/http/endpoint.py13
2 files changed, 40 insertions, 4 deletions
diff --git a/synapse/handlers/federation.py b/synapse/handlers/federation.py
index 0c68e8a472..f10b46414b 100644
--- a/synapse/handlers/federation.py
+++ b/synapse/handlers/federation.py
@@ -360,6 +360,35 @@ class FederationHandler(BaseHandler):
         # apparently.
         #
         # see https://github.com/matrix-org/synapse/pull/1744
+        #
+        # ----
+        #
+        # Update richvdh 2018/09/18: There are a number of problems with timing this
+        # request out agressively on the client side:
+        #
+        # - it plays badly with the server-side rate-limiter, which starts tarpitting you
+        #   if you send too many requests at once, so you end up with the server carefully
+        #   working through the backlog of your requests, which you have already timed
+        #   out.
+        #
+        # - for this request in particular, we now (as of
+        #   https://github.com/matrix-org/synapse/pull/3456) reject any PDUs where the
+        #   server can't produce a plausible-looking set of prev_events - so we becone
+        #   much more likely to reject the event.
+        #
+        # - contrary to what it says above, we do *not* fall back to fetching fresh state
+        #   for the room if get_missing_events times out. Rather, we give up processing
+        #   the PDU whose prevs we are missing, which then makes it much more likely that
+        #   we'll end up back here for the *next* PDU in the list, which exacerbates the
+        #   problem.
+        #
+        # - the agressive 10s timeout was introduced to deal with incoming federation
+        #   requests taking 8 hours to process. It's not entirely clear why that was going
+        #   on; certainly there were other issues causing traffic storms which are now
+        #   resolved, and I think in any case we may be more sensible about our locking
+        #   now. We're *certainly* more sensible about our logging.
+        #
+        # All that said: Let's try increasing the timout to 60s and see what happens.
 
         missing_events = yield self.federation_client.get_missing_events(
             origin,
@@ -368,7 +397,7 @@ class FederationHandler(BaseHandler):
             latest_events=[pdu],
             limit=10,
             min_depth=min_depth,
-            timeout=10000,
+            timeout=60000,
         )
 
         logger.info(
diff --git a/synapse/http/endpoint.py b/synapse/http/endpoint.py
index b0c9369519..91025037a3 100644
--- a/synapse/http/endpoint.py
+++ b/synapse/http/endpoint.py
@@ -108,7 +108,7 @@ def matrix_federation_endpoint(reactor, destination, tls_client_options_factory=
 
     Args:
         reactor: Twisted reactor.
-        destination (bytes): The name of the server to connect to.
+        destination (unicode): The name of the server to connect to.
         tls_client_options_factory
             (synapse.crypto.context_factory.ClientTLSOptionsFactory):
             Factory which generates TLS options for client connections.
@@ -126,10 +126,17 @@ def matrix_federation_endpoint(reactor, destination, tls_client_options_factory=
         transport_endpoint = HostnameEndpoint
         default_port = 8008
     else:
+        # the SNI string should be the same as the Host header, minus the port.
+        # as per https://github.com/matrix-org/synapse/issues/2525#issuecomment-336896777,
+        # the Host header and SNI should therefore be the server_name of the remote
+        # server.
+        tls_options = tls_client_options_factory.get_options(domain)
+
         def transport_endpoint(reactor, host, port, timeout):
             return wrapClientTLS(
-                tls_client_options_factory.get_options(host),
-                HostnameEndpoint(reactor, host, port, timeout=timeout))
+                tls_options,
+                HostnameEndpoint(reactor, host, port, timeout=timeout),
+            )
         default_port = 8448
 
     if port is None: