public inbox for [email protected]
help / color / mirror / Atom feedFrom: Kyotaro Horiguchi <[email protected]>
Subject: [PATCH] Remove entries that haven't been used for a certain time
Date: Fri, 1 Mar 2019 13:32:51 +0900
Catcache entries happen to be left alone for several reasons. It is
not desirable that such useless entries eat up memory. Catcache
pruning feature removes entries that haven't been accessed for a
certain time before enlarging hash array.
---
doc/src/sgml/config.sgml | 19 +++++
src/backend/tcop/postgres.c | 2 +
src/backend/utils/cache/catcache.c | 105 +++++++++++++++++++++++++-
src/backend/utils/misc/guc.c | 12 +++
src/backend/utils/misc/postgresql.conf.sample | 1 +
src/include/utils/catcache.h | 16 ++++
6 files changed, 152 insertions(+), 3 deletions(-)
diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index d383de2512..4231235447 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -1677,6 +1677,25 @@ include_dir 'conf.d'
</listitem>
</varlistentry>
+ <varlistentry id="guc-catalog-cache-prune-min-age" xreflabel="catalog_cache_prune_min_age">
+ <term><varname>catalog_cache_prune_min_age</varname> (<type>integer</type>)
+ <indexterm>
+ <primary><varname>catalog_cache_prune_min_age</varname> configuration
+ parameter</primary>
+ </indexterm>
+ </term>
+ <listitem>
+ <para>
+ Specifies the minimum amount of unused time in seconds at which a
+ system catalog cache entry is removed. -1 indicates that this feature
+ is disabled at all. The value defaults to 300 seconds (<literal>5
+ minutes</literal>). The entries that are not used for the duration
+ can be removed to prevent catalog cache from bloating with useless
+ entries.
+ </para>
+ </listitem>
+ </varlistentry>
+
<varlistentry id="guc-max-stack-depth" xreflabel="max_stack_depth">
<term><varname>max_stack_depth</varname> (<type>integer</type>)
<indexterm>
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index f9ce3d8f22..acab473d34 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -71,6 +71,7 @@
#include "tcop/pquery.h"
#include "tcop/tcopprot.h"
#include "tcop/utility.h"
+#include "utils/catcache.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
#include "utils/ps_status.h"
@@ -2575,6 +2576,7 @@ start_xact_command(void)
* not desired, the timeout has to be disabled explicitly.
*/
enable_statement_timeout();
+ SetCatCacheClock(GetCurrentStatementStartTimestamp());
}
static void
diff --git a/src/backend/utils/cache/catcache.c b/src/backend/utils/cache/catcache.c
index d05930bc4c..52586bd415 100644
--- a/src/backend/utils/cache/catcache.c
+++ b/src/backend/utils/cache/catcache.c
@@ -38,6 +38,7 @@
#include "utils/rel.h"
#include "utils/resowner_private.h"
#include "utils/syscache.h"
+#include "utils/timeout.h"
/* #define CACHEDEBUG */ /* turns DEBUG elogs on */
@@ -60,9 +61,18 @@
#define CACHE_elog(...)
#endif
+/*
+ * GUC variable to define the minimum age of entries that will be considered
+ * to be evicted in seconds. -1 to disable the feature.
+ */
+int catalog_cache_prune_min_age = 300;
+
/* Cache management header --- pointer is NULL until created */
static CatCacheHeader *CacheHdr = NULL;
+/* Clock for the last accessed time of a catcache entry. */
+TimestampTz catcacheclock = 0;
+
static inline HeapTuple SearchCatCacheInternal(CatCache *cache,
int nkeys,
Datum v1, Datum v2,
@@ -850,9 +860,83 @@ InitCatCache(int id,
*/
MemoryContextSwitchTo(oldcxt);
+ /* initialize catcache reference clock if haven't done yet */
+ if (catcacheclock == 0)
+ catcacheclock = GetCurrentTimestamp();
+
return cp;
}
+/*
+ * CatCacheCleanupOldEntries - Remove infrequently-used entries
+ *
+ * Catcache entries happen to be left unused for a long time for several
+ * reasons. Remove such entries to prevent catcache from bloating. It is based
+ * on the similar algorithm with buffer eviction. Entries that are accessed
+ * several times in a certain period live longer than those that have had less
+ * access in the same duration.
+ */
+static bool
+CatCacheCleanupOldEntries(CatCache *cp)
+{
+ int nremoved = 0;
+ int i;
+
+ /* Return immediately if disabled */
+ if (catalog_cache_prune_min_age == 0)
+ return false;
+
+ /* Scan over the whole hash to find entries to remove */
+ for (i = 0 ; i < cp->cc_nbuckets ; i++)
+ {
+ dlist_mutable_iter iter;
+
+ dlist_foreach_modify(iter, &cp->cc_bucket[i])
+ {
+ CatCTup *ct = dlist_container(CatCTup, cache_elem, iter.cur);
+ long entry_age;
+ int us;
+
+ /* Don't remove referenced entries */
+ if (ct->refcount != 0 ||
+ (ct->c_list && ct->c_list->refcount != 0))
+ continue;
+
+ /*
+ * Calculate the duration from the time from the last access to
+ * the "current" time. catcacheclock is updated per-statement
+ * basis and additionaly udpated periodically during a long
+ * running query.
+ */
+ TimestampDifference(ct->lastaccess, catcacheclock, &entry_age, &us);
+
+ if (entry_age < catalog_cache_prune_min_age)
+ continue;
+
+ /*
+ * Entries that are not accessed after the last pruning are
+ * removed in that seconds, and their lives are prolonged
+ * according to how many times they are accessed up to three times
+ * of the duration. We don't try shrink buckets since pruning
+ * effectively caps catcache expansion in the long term.
+ */
+ if (ct->naccess > 0)
+ ct->naccess--;
+ else
+ {
+ CatCacheRemoveCTup(cp, ct);
+ nremoved++;
+ }
+ }
+ }
+
+ if (nremoved > 0)
+ elog(DEBUG1, "pruning catalog cache id=%d for %s: removed %d / %d",
+ cp->id, cp->cc_relname, nremoved, cp->cc_ntup + nremoved);
+
+ return nremoved > 0;
+}
+
/*
* Enlarge a catcache, doubling the number of buckets.
*/
@@ -1264,6 +1348,12 @@ SearchCatCacheInternal(CatCache *cache,
*/
dlist_move_head(bucket, &ct->cache_elem);
+ /* prolong life of this entry */
+ if (ct->naccess < 2)
+ ct->naccess++;
+
+ ct->lastaccess = catcacheclock;
+
/*
* If it's a positive entry, bump its refcount and return it. If it's
* negative, we can report failure to the caller.
@@ -1888,19 +1978,28 @@ CatalogCacheCreateEntry(CatCache *cache, HeapTuple ntp, Datum *arguments,
ct->dead = false;
ct->negative = negative;
ct->hash_value = hashValue;
+ ct->naccess = 0;
+ ct->lastaccess = catcacheclock;
dlist_push_head(&cache->cc_bucket[hashIndex], &ct->cache_elem);
cache->cc_ntup++;
CacheHdr->ch_ntup++;
+ /* increase refcount so that the new entry survives pruning */
+ ct->refcount++;
+
/*
- * If the hash table has become too full, enlarge the buckets array. Quite
- * arbitrarily, we enlarge when fill factor > 2.
+ * If the hash table has become too full, try removing infrequently used
+ * entries to make a room for the new entry. If failed, enlarge the bucket
+ * array instead. Quite arbitrarily, we try this when fill factor > 2.
*/
- if (cache->cc_ntup > cache->cc_nbuckets * 2)
+ if (cache->cc_ntup > cache->cc_nbuckets * 2 &&
+ !CatCacheCleanupOldEntries(cache))
RehashCatCache(cache);
+ ct->refcount--;
+
return ct;
}
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index aa564d153a..e624c74bf9 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -82,6 +82,7 @@
#include "tsearch/ts_cache.h"
#include "utils/builtins.h"
#include "utils/bytea.h"
+#include "utils/catcache.h"
#include "utils/guc_tables.h"
#include "utils/float.h"
#include "utils/memutils.h"
@@ -2202,6 +2203,17 @@ static struct config_int ConfigureNamesInt[] =
NULL, NULL, NULL
},
+ {
+ {"catalog_cache_prune_min_age", PGC_USERSET, RESOURCES_MEM,
+ gettext_noop("System catalog cache entries that live unused for longer than this seconds are considered for removal."),
+ gettext_noop("The value of -1 turns off pruning."),
+ GUC_UNIT_S
+ },
+ &catalog_cache_prune_min_age,
+ 300, -1, INT_MAX,
+ NULL, NULL, NULL
+ },
+
/*
* We use the hopefully-safely-small value of 100kB as the compiled-in
* default for max_stack_depth. InitializeGUCOptions will increase it if
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index cccb5f145a..fa117f0573 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -128,6 +128,7 @@
#work_mem = 4MB # min 64kB
#maintenance_work_mem = 64MB # min 1MB
#autovacuum_work_mem = -1 # min 1MB, or -1 to use maintenance_work_mem
+#catalog_cache_prune_min_age = 300s # -1 disables pruning
#max_stack_depth = 2MB # min 100kB
#shared_memory_type = mmap # the default is the first option
# supported by the operating system:
diff --git a/src/include/utils/catcache.h b/src/include/utils/catcache.h
index 65d816a583..2134839ecf 100644
--- a/src/include/utils/catcache.h
+++ b/src/include/utils/catcache.h
@@ -22,6 +22,7 @@
#include "access/htup.h"
#include "access/skey.h"
+#include "datatype/timestamp.h"
#include "lib/ilist.h"
#include "utils/relcache.h"
@@ -119,6 +120,8 @@ typedef struct catctup
bool dead; /* dead but not yet removed? */
bool negative; /* negative cache entry? */
HeapTupleData tuple; /* tuple management header */
+ int naccess; /* # of access to this entry, up to 2 */
+ TimestampTz lastaccess; /* timestamp of the last usage */
/*
* The tuple may also be a member of at most one CatCList. (If a single
@@ -189,6 +192,19 @@ typedef struct catcacheheader
/* this extern duplicates utils/memutils.h... */
extern PGDLLIMPORT MemoryContext CacheMemoryContext;
+/* for guc.c, not PGDLLPMPORT'ed */
+extern int catalog_cache_prune_min_age;
+
+/* source clock for access timestamp of catcache entries */
+extern TimestampTz catcacheclock;
+
+/* SetCatCacheClock - set catcache timestamp source clodk */
+static inline void
+SetCatCacheClock(TimestampTz ts)
+{
+ catcacheclock = ts;
+}
+
extern void CreateCacheMemoryContext(void);
extern CatCache *InitCatCache(int id, Oid reloid, Oid indexoid,
--
2.16.3
----Next_Part(Fri_Mar_29_17_24_40_2019_805)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
filename="FullScan-mod-0001-Remove-entries-that-haven-t-been-used-for-a-certain-.patch"
view thread (18+ messages) latest in thread
reply
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: [email protected]
Cc: [email protected]
Subject: Re: [PATCH] Remove entries that haven't been used for a certain time
In-Reply-To: <no-message-id-1883731@localhost>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox