From bc496df192fa20dee933590d5f21a3425388c0d7 Mon Sep 17 00:00:00 2001 From: Richard van der Hoff Date: Thu, 1 Feb 2018 17:57:51 +0000 Subject: report metrics on number of cache evictions --- synapse/util/caches/descriptors.py | 4 ++++ synapse/util/caches/expiringcache.py | 6 +++++- synapse/util/caches/lrucache.py | 28 +++++++++++++++++++++++++--- 3 files changed, 34 insertions(+), 4 deletions(-) (limited to 'synapse/util/caches') diff --git a/synapse/util/caches/descriptors.py b/synapse/util/caches/descriptors.py index af65bfe7b8..bf3a66eae4 100644 --- a/synapse/util/caches/descriptors.py +++ b/synapse/util/caches/descriptors.py @@ -75,6 +75,7 @@ class Cache(object): self.cache = LruCache( max_size=max_entries, keylen=keylen, cache_type=cache_type, size_callback=(lambda d: len(d)) if iterable else None, + evicted_callback=self._on_evicted, ) self.name = name @@ -83,6 +84,9 @@ class Cache(object): self.thread = None self.metrics = register_cache(name, self.cache) + def _on_evicted(self, evicted_count): + self.metrics.inc_evictions(evicted_count) + def check_thread(self): expected_thread = self.thread if expected_thread is None: diff --git a/synapse/util/caches/expiringcache.py b/synapse/util/caches/expiringcache.py index 6ad53a6390..0aa103eecb 100644 --- a/synapse/util/caches/expiringcache.py +++ b/synapse/util/caches/expiringcache.py @@ -79,7 +79,11 @@ class ExpiringCache(object): while self._max_len and len(self) > self._max_len: _key, value = self._cache.popitem(last=False) if self.iterable: - self._size_estimate -= len(value.value) + removed_len = len(value.value) + self.metrics.inc_evictions(removed_len) + self._size_estimate -= removed_len + else: + self.metrics.inc_evictions() def __getitem__(self, key): try: diff --git a/synapse/util/caches/lrucache.py b/synapse/util/caches/lrucache.py index cf5fbb679c..f088dd430e 100644 --- a/synapse/util/caches/lrucache.py +++ b/synapse/util/caches/lrucache.py @@ -49,7 +49,24 @@ class LruCache(object): Can also set callbacks on objects when getting/setting which are fired when that key gets invalidated/evicted. """ - def __init__(self, max_size, keylen=1, cache_type=dict, size_callback=None): + def __init__(self, max_size, keylen=1, cache_type=dict, size_callback=None, + evicted_callback=None): + """ + Args: + max_size (int): + + keylen (int): + + cache_type (type): + type of underlying cache to be used. Typically one of dict + or TreeCache. + + size_callback (func(V) -> int | None): + + evicted_callback (func(int)|None): + if not None, called on eviction with the size of the evicted + entry + """ cache = cache_type() self.cache = cache # Used for introspection. list_root = _Node(None, None, None, None) @@ -61,8 +78,10 @@ class LruCache(object): def evict(): while cache_len() > max_size: todelete = list_root.prev_node - delete_node(todelete) + evicted_len = delete_node(todelete) cache.pop(todelete.key, None) + if evicted_callback: + evicted_callback(evicted_len) def synchronized(f): @wraps(f) @@ -111,12 +130,15 @@ class LruCache(object): prev_node.next_node = next_node next_node.prev_node = prev_node + deleted_len = 1 if size_callback: - cached_cache_len[0] -= size_callback(node.value) + deleted_len = size_callback(node.value) + cached_cache_len[0] -= deleted_len for cb in node.callbacks: cb() node.callbacks.clear() + return deleted_len @synchronized def cache_get(key, default=None, callbacks=[]): -- cgit 1.5.1 From 7c7706f42b56dd61f5eb17679aa12247f7058ed5 Mon Sep 17 00:00:00 2001 From: Erik Johnston Date: Thu, 15 Mar 2018 15:40:13 +0000 Subject: Fix bug where state cache used lots of memory The state cache bases its size on the sum of the size of entries. The size of the entry is calculated once on insertion, so it is important that the size of entries does not change. The DictionaryCache modified the entries size, which caused the state cache to incorrectly think it was smaller than it actually was. --- synapse/util/caches/dictionary_cache.py | 6 +++++- synapse/util/caches/lrucache.py | 8 ++++---- 2 files changed, 9 insertions(+), 5 deletions(-) (limited to 'synapse/util/caches') diff --git a/synapse/util/caches/dictionary_cache.py b/synapse/util/caches/dictionary_cache.py index d4105822b3..1709e8b429 100644 --- a/synapse/util/caches/dictionary_cache.py +++ b/synapse/util/caches/dictionary_cache.py @@ -132,9 +132,13 @@ class DictionaryCache(object): self._update_or_insert(key, value, known_absent) def _update_or_insert(self, key, value, known_absent): - entry = self.cache.setdefault(key, DictionaryEntry(False, set(), {})) + # We pop and reinsert as we need to tell the cache the size may have + # changed + + entry = self.cache.pop(key, DictionaryEntry(False, set(), {})) entry.value.update(value) entry.known_absent.update(known_absent) + self.cache[key] = entry def _insert(self, key, value, known_absent): self.cache[key] = DictionaryEntry(True, known_absent, value) diff --git a/synapse/util/caches/lrucache.py b/synapse/util/caches/lrucache.py index f088dd430e..a4bf8fa6ae 100644 --- a/synapse/util/caches/lrucache.py +++ b/synapse/util/caches/lrucache.py @@ -154,14 +154,14 @@ class LruCache(object): def cache_set(key, value, callbacks=[]): node = cache.get(key, None) if node is not None: - if value != node.value: + if node.callbacks and value != node.value: for cb in node.callbacks: cb() node.callbacks.clear() - if size_callback: - cached_cache_len[0] -= size_callback(node.value) - cached_cache_len[0] += size_callback(value) + if size_callback: + cached_cache_len[0] -= size_callback(node.value) + cached_cache_len[0] += size_callback(value) node.callbacks.update(callbacks) -- cgit 1.5.1 From 9a0d783c113ae74c55e409d33219cd77f3662b9f Mon Sep 17 00:00:00 2001 From: Erik Johnston Date: Mon, 19 Mar 2018 11:35:53 +0000 Subject: Add comments --- synapse/util/caches/lrucache.py | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'synapse/util/caches') diff --git a/synapse/util/caches/lrucache.py b/synapse/util/caches/lrucache.py index a4bf8fa6ae..1c5a982094 100644 --- a/synapse/util/caches/lrucache.py +++ b/synapse/util/caches/lrucache.py @@ -154,11 +154,18 @@ class LruCache(object): def cache_set(key, value, callbacks=[]): node = cache.get(key, None) if node is not None: + # We sometimes store large objects, e.g. dicts, which cause + # the inequality check to take a long time. So let's only do + # the check if we have some callbacks to call. if node.callbacks and value != node.value: for cb in node.callbacks: cb() node.callbacks.clear() + # We don't bother to protect this by value != node.value as + # generally size_callback will be cheap compared with equality + # checks. (For example, taking the size of two dicts is quicker + # than comparing them for equality.) if size_callback: cached_cache_len[0] -= size_callback(node.value) cached_cache_len[0] += size_callback(value) -- cgit 1.5.1