Refactor request sending to have better excpetions (#4358)

* Correctly retry and back off if we get a HTTPerror response

* Refactor request sending to have better excpetions

MatrixFederationHttpClient blindly reraised exceptions to the caller
without differentiating "expected" failures (e.g. connection timeouts
etc) versus more severe problems (e.g. programming errors).

This commit adds a RequestSendFailed exception that is raised when
"expected" failures happen, allowing the TransactionQueue to log them as
warnings while allowing us to log other exceptions as actual exceptions.

1 files changed, 14 insertions, 5 deletions

diff --git a/synapse/federation/transaction_queue.py b/synapse/federation/transaction_queue.py
index 099ace28c1..4640513497 100644
--- a/synapse/federation/transaction_queue.py
+++ b/synapse/federation/transaction_queue.py
@@ -22,7 +22,11 @@ from prometheus_client import Counter
 from twisted.internet import defer
 
 import synapse.metrics
-from synapse.api.errors import FederationDeniedError, HttpResponseException
+from synapse.api.errors import (
+    FederationDeniedError,
+    HttpResponseException,
+    RequestSendFailed,
+)
 from synapse.handlers.presence import format_user_presence_state, get_interested_remotes
 from synapse.metrics import (
     LaterGauge,
@@ -518,11 +522,16 @@ class TransactionQueue(object):
             )
         except FederationDeniedError as e:
             logger.info(e)
-        except Exception as e:
-            logger.warn(
-                "TX [%s] Failed to send transaction: %s",
+        except RequestSendFailed as e:
+            logger.warning("(TX [%s] Failed to send transaction: %s", destination, e)
+
+            for p, _ in pending_pdus:
+                logger.info("Failed to send event %s to %s", p.event_id,
+                            destination)
+        except Exception:
+            logger.exception(
+                "TX [%s] Failed to send transaction",
                 destination,
-                e,
             )
             for p, _ in pending_pdus:
                 logger.info("Failed to send event %s to %s", p.event_id,