From 1fb9a2d0bf2506ca6e5343cb340a441585ca1c07 Mon Sep 17 00:00:00 2001
From: Erik Johnston <erik@matrix.org>
Date: Wed, 5 May 2021 16:53:45 +0100
Subject: Limit how often GC happens by time. (#9902)

Synapse can be quite memory intensive, and unless care is taken to tune
the GC thresholds it can end up thrashing, causing noticable performance
problems for large servers. We fix this by limiting how often we GC a
given generation, regardless of current counts/thresholds.

This does not help with the reverse problem where the thresholds are set
too high, but that should only happen in situations where they've been
manually configured.

Adds a `gc_min_seconds_between` config option to override the defaults.

Fixes #9890.
---
 synapse/config/server.py | 31 ++++++++++++++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

(limited to 'synapse/config')

diff --git a/synapse/config/server.py b/synapse/config/server.py
index 21ca7b33e3..c290a35a92 100644
--- a/synapse/config/server.py
+++ b/synapse/config/server.py
@@ -19,7 +19,7 @@ import logging
 import os.path
 import re
 from textwrap import indent
-from typing import Any, Dict, Iterable, List, Optional, Set
+from typing import Any, Dict, Iterable, List, Optional, Set, Tuple
 
 import attr
 import yaml
@@ -572,6 +572,7 @@ class ServerConfig(Config):
             _warn_if_webclient_configured(self.listeners)
 
         self.gc_thresholds = read_gc_thresholds(config.get("gc_thresholds", None))
+        self.gc_seconds = self.read_gc_intervals(config.get("gc_min_interval", None))
 
         @attr.s
         class LimitRemoteRoomsConfig:
@@ -917,6 +918,16 @@ class ServerConfig(Config):
         #
         #gc_thresholds: [700, 10, 10]
 
+        # The minimum time in seconds between each GC for a generation, regardless of
+        # the GC thresholds. This ensures that we don't do GC too frequently.
+        #
+        # A value of `[1s, 10s, 30s]` indicates that a second must pass between consecutive
+        # generation 0 GCs, etc.
+        #
+        # Defaults to `[1s, 10s, 30s]`.
+        #
+        #gc_min_interval: [0.5s, 30s, 1m]
+
         # Set the limit on the returned events in the timeline in the get
         # and sync operations. The default value is 100. -1 means no upper limit.
         #
@@ -1305,6 +1316,24 @@ class ServerConfig(Config):
             help="Turn on the twisted telnet manhole service on the given port.",
         )
 
+    def read_gc_intervals(self, durations) -> Optional[Tuple[float, float, float]]:
+        """Reads the three durations for the GC min interval option, returning seconds."""
+        if durations is None:
+            return None
+
+        try:
+            if len(durations) != 3:
+                raise ValueError()
+            return (
+                self.parse_duration(durations[0]) / 1000,
+                self.parse_duration(durations[1]) / 1000,
+                self.parse_duration(durations[2]) / 1000,
+            )
+        except Exception:
+            raise ConfigError(
+                "Value of `gc_min_interval` must be a list of three durations if set"
+            )
+
 
 def is_threepid_reserved(reserved_threepids, threepid):
     """Check the threepid against the reserved threepid config
-- 
cgit 1.4.1