Allow for the configuration of max request retries and min/max retry delays in the matrix federation client (#12504)

Co-authored-by: Mathieu Velten <mathieuv@matrix.org>
Co-authored-by: Erik Johnston <erik@matrix.org>

2 files changed, 22 insertions, 9 deletions

diff --git a/synapse/config/federation.py b/synapse/config/federation.py

index 336fca578a..d21f7fd02a 100644
--- a/synapse/config/federation.py
+++ b/synapse/config/federation.py
@@ -22,6 +22,8 @@ class FederationConfig(Config):
     section = "federation"
 
     def read_config(self, config: JsonDict, **kwargs: Any) -> None:
+        federation_config = config.setdefault("federation", {})
+
         # FIXME: federation_domain_whitelist needs sytests
         self.federation_domain_whitelist: Optional[dict] = None
         federation_domain_whitelist = config.get("federation_domain_whitelist", None)
@@ -49,5 +51,13 @@ class FederationConfig(Config):
             "allow_device_name_lookup_over_federation", False
         )
 
+        # Allow for the configuration of timeout, max request retries
+        # and min/max retry delays in the matrix federation client.
+        self.client_timeout = federation_config.get("client_timeout", 60)
+        self.max_long_retry_delay = federation_config.get("max_long_retry_delay", 60)
+        self.max_short_retry_delay = federation_config.get("max_short_retry_delay", 2)
+        self.max_long_retries = federation_config.get("max_long_retries", 10)
+        self.max_short_retries = federation_config.get("max_short_retries", 3)
+
 
 _METRICS_FOR_DOMAINS_SCHEMA = {"type": "array", "items": {"type": "string"}}
diff --git a/synapse/http/matrixfederationclient.py b/synapse/http/matrixfederationclient.py

index abb5ae5815..ed36825b67 100644
--- a/synapse/http/matrixfederationclient.py
+++ b/synapse/http/matrixfederationclient.py
@@ -95,8 +95,6 @@ incoming_responses_counter = Counter(
 )
 
 
-MAX_LONG_RETRIES = 10
-MAX_SHORT_RETRIES = 3
 MAXINT = sys.maxsize
 
 
@@ -406,7 +404,12 @@ class MatrixFederationHttpClient:
         self.clock = hs.get_clock()
         self._store = hs.get_datastores().main
         self.version_string_bytes = hs.version_string.encode("ascii")
-        self.default_timeout = 60
+        self.default_timeout = hs.config.federation.client_timeout
+
+        self.max_long_retry_delay = hs.config.federation.max_long_retry_delay
+        self.max_short_retry_delay = hs.config.federation.max_short_retry_delay
+        self.max_long_retries = hs.config.federation.max_long_retries
+        self.max_short_retries = hs.config.federation.max_short_retries
 
         self._cooperator = Cooperator(scheduler=_make_scheduler(self.reactor))
 
@@ -583,9 +586,9 @@ class MatrixFederationHttpClient:
             # XXX: Would be much nicer to retry only at the transaction-layer
             # (once we have reliable transactions in place)
             if long_retries:
-                retries_left = MAX_LONG_RETRIES
+                retries_left = self.max_long_retries
             else:
-                retries_left = MAX_SHORT_RETRIES
+                retries_left = self.max_short_retries
 
             url_bytes = request.uri
             url_str = url_bytes.decode("ascii")
@@ -730,12 +733,12 @@ class MatrixFederationHttpClient:
 
                     if retries_left and not timeout:
                         if long_retries:
-                            delay = 4 ** (MAX_LONG_RETRIES + 1 - retries_left)
-                            delay = min(delay, 60)
+                            delay = 4 ** (self.max_long_retries + 1 - retries_left)
+                            delay = min(delay, self.max_long_retry_delay)
                             delay *= random.uniform(0.8, 1.4)
                         else:
-                            delay = 0.5 * 2 ** (MAX_SHORT_RETRIES - retries_left)
-                            delay = min(delay, 2)
+                            delay = 0.5 * 2 ** (self.max_short_retries - retries_left)
+                            delay = min(delay, self.max_short_retry_delay)
                             delay *= random.uniform(0.8, 1.4)
 
                         logger.debug(