Add support for evicting cache entries based on last access time. (#10205)

Author: erikjohnston

changelog.d/10205.feature

@@ -0,0 +1 @@
+Add support for evicting cache entries based on last access time.

docs/sample_config.yaml

@@ -673,35 +673,41 @@ retention:
 #event_cache_size: 10K
 
 caches:
-   # Controls the global cache factor, which is the default cache factor
-   # for all caches if a specific factor for that cache is not otherwise
-   # set.
-   #
-   # This can also be set by the "SYNAPSE_CACHE_FACTOR" environment
-   # variable. Setting by environment variable takes priority over
-   # setting through the config file.
-   #
-   # Defaults to 0.5, which will half the size of all caches.
-   #
-   #global_factor: 1.0
+  # Controls the global cache factor, which is the default cache factor
+  # for all caches if a specific factor for that cache is not otherwise
+  # set.
+  #
+  # This can also be set by the "SYNAPSE_CACHE_FACTOR" environment
+  # variable. Setting by environment variable takes priority over
+  # setting through the config file.
+  #
+  # Defaults to 0.5, which will half the size of all caches.
+  #
+  #global_factor: 1.0
 
-   # A dictionary of cache name to cache factor for that individual
-   # cache. Overrides the global cache factor for a given cache.
-   #
-   # These can also be set through environment variables comprised
-   # of "SYNAPSE_CACHE_FACTOR_" + the name of the cache in capital
-   # letters and underscores. Setting by environment variable
-   # takes priority over setting through the config file.
-   # Ex. SYNAPSE_CACHE_FACTOR_GET_USERS_WHO_SHARE_ROOM_WITH_USER=2.0
-   #
-   # Some caches have '*' and other characters that are not
-   # alphanumeric or underscores. These caches can be named with or
-   # without the special characters stripped. For example, to specify
-   # the cache factor for `*stateGroupCache*` via an environment
-   # variable would be `SYNAPSE_CACHE_FACTOR_STATEGROUPCACHE=2.0`.
-   #
-   per_cache_factors:
-     #get_users_who_share_room_with_user: 2.0
+  # A dictionary of cache name to cache factor for that individual
+  # cache. Overrides the global cache factor for a given cache.
+  #
+  # These can also be set through environment variables comprised
+  # of "SYNAPSE_CACHE_FACTOR_" + the name of the cache in capital
+  # letters and underscores. Setting by environment variable
+  # takes priority over setting through the config file.
+  # Ex. SYNAPSE_CACHE_FACTOR_GET_USERS_WHO_SHARE_ROOM_WITH_USER=2.0
+  #
+  # Some caches have '*' and other characters that are not
+  # alphanumeric or underscores. These caches can be named with or
+  # without the special characters stripped. For example, to specify
+  # the cache factor for `*stateGroupCache*` via an environment
+  # variable would be `SYNAPSE_CACHE_FACTOR_STATEGROUPCACHE=2.0`.
+  #
+  per_cache_factors:
+    #get_users_who_share_room_with_user: 2.0
+
+  # Controls how long an entry can be in a cache without having been
+  # accessed before being evicted. Defaults to None, which means
+  # entries are never evicted based on time.
+  #
+  #expiry_time: 30m
 
 
 ## Database ##

mypy.ini

@@ -75,6 +75,7 @@ files =
   synapse/util/daemonize.py,
   synapse/util/hash.py,
   synapse/util/iterutils.py,
+  synapse/util/linked_list.py,
   synapse/util/metrics.py,
   synapse/util/macaroons.py,
   synapse/util/module_loader.py,

synapse/app/_base.py

@@ -21,7 +21,7 @@
 import sys
 import traceback
 import warnings
-from typing import Awaitable, Callable, Iterable
+from typing import TYPE_CHECKING, Awaitable, Callable, Iterable
 
 from cryptography.utils import CryptographyDeprecationWarning
 from typing_extensions import NoReturn
@@ -41,10 +41,14 @@
 from synapse.logging.context import PreserveLoggingContext
 from synapse.metrics.background_process_metrics import wrap_as_background_process
 from synapse.metrics.jemalloc import setup_jemalloc_stats
+from synapse.util.caches.lrucache import setup_expire_lru_cache_entries
 from synapse.util.daemonize import daemonize_process
 from synapse.util.rlimit import change_resource_limit
 from synapse.util.versionstring import get_version_string
 
+if TYPE_CHECKING:
+    from synapse.server import HomeServer
+
 logger = logging.getLogger(__name__)
 
 # list of tuples of function, args list, kwargs dict
@@ -312,7 +316,7 @@ def refresh_certificate(hs):
         logger.info("Context factories updated.")
 
 
-async def start(hs: "synapse.server.HomeServer"):
+async def start(hs: "HomeServer"):
     """
     Start a Synapse server or worker.
 
@@ -365,6 +369,9 @@ def run_sighup(*args, **kwargs):
 
     load_legacy_spam_checkers(hs)
 
+    # If we've configured an expiry time for caches, start the background job now.
+    setup_expire_lru_cache_entries(hs)
+
     # It is now safe to start your Synapse.
     hs.start_listening()
     hs.get_datastore().db_pool.start_profiling()

synapse/config/_base.pyi

@@ -5,6 +5,7 @@ from synapse.config import (
     api,
     appservice,
     auth,
+    cache,
     captcha,
     cas,
     consent,
@@ -88,6 +89,7 @@ class RootConfig:
     tracer: tracer.TracerConfig
     redis: redis.RedisConfig
     modules: modules.ModulesConfig
+    caches: cache.CacheConfig
     federation: federation.FederationConfig
 
     config_classes: List = ...

synapse/config/cache.py

@@ -116,35 +116,41 @@ def generate_config_section(self, **kwargs):
         #event_cache_size: 10K
 
         caches:
-           # Controls the global cache factor, which is the default cache factor
-           # for all caches if a specific factor for that cache is not otherwise
-           # set.
-           #
-           # This can also be set by the "SYNAPSE_CACHE_FACTOR" environment
-           # variable. Setting by environment variable takes priority over
-           # setting through the config file.
-           #
-           # Defaults to 0.5, which will half the size of all caches.
-           #
-           #global_factor: 1.0
-
-           # A dictionary of cache name to cache factor for that individual
-           # cache. Overrides the global cache factor for a given cache.
-           #
-           # These can also be set through environment variables comprised
-           # of "SYNAPSE_CACHE_FACTOR_" + the name of the cache in capital
-           # letters and underscores. Setting by environment variable
-           # takes priority over setting through the config file.
-           # Ex. SYNAPSE_CACHE_FACTOR_GET_USERS_WHO_SHARE_ROOM_WITH_USER=2.0
-           #
-           # Some caches have '*' and other characters that are not
-           # alphanumeric or underscores. These caches can be named with or
-           # without the special characters stripped. For example, to specify
-           # the cache factor for `*stateGroupCache*` via an environment
-           # variable would be `SYNAPSE_CACHE_FACTOR_STATEGROUPCACHE=2.0`.
-           #
-           per_cache_factors:
-             #get_users_who_share_room_with_user: 2.0
+          # Controls the global cache factor, which is the default cache factor
+          # for all caches if a specific factor for that cache is not otherwise
+          # set.
+          #
+          # This can also be set by the "SYNAPSE_CACHE_FACTOR" environment
+          # variable. Setting by environment variable takes priority over
+          # setting through the config file.
+          #
+          # Defaults to 0.5, which will half the size of all caches.
+          #
+          #global_factor: 1.0
+
+          # A dictionary of cache name to cache factor for that individual
+          # cache. Overrides the global cache factor for a given cache.
+          #
+          # These can also be set through environment variables comprised
+          # of "SYNAPSE_CACHE_FACTOR_" + the name of the cache in capital
+          # letters and underscores. Setting by environment variable
+          # takes priority over setting through the config file.
+          # Ex. SYNAPSE_CACHE_FACTOR_GET_USERS_WHO_SHARE_ROOM_WITH_USER=2.0
+          #
+          # Some caches have '*' and other characters that are not
+          # alphanumeric or underscores. These caches can be named with or
+          # without the special characters stripped. For example, to specify
+          # the cache factor for `*stateGroupCache*` via an environment
+          # variable would be `SYNAPSE_CACHE_FACTOR_STATEGROUPCACHE=2.0`.
+          #
+          per_cache_factors:
+            #get_users_who_share_room_with_user: 2.0
+
+          # Controls how long an entry can be in a cache without having been
+          # accessed before being evicted. Defaults to None, which means
+          # entries are never evicted based on time.
+          #
+          #expiry_time: 30m
         """
 
     def read_config(self, config, **kwargs):
@@ -200,6 +206,12 @@ def read_config(self, config, **kwargs):
                     e.message  # noqa: B306, DependencyException.message is a property
                 )
 
+        expiry_time = cache_config.get("expiry_time")
+        if expiry_time:
+            self.expiry_time_msec = self.parse_duration(expiry_time)
+        else:
+            self.expiry_time_msec = None
+
         # Resize all caches (if necessary) with the new factors we've loaded
         self.resize_all_caches()