Re: Protect syscache from bloating with negative cache entries - Mailing list pgsql-hackers

From Kyotaro HORIGUCHI
Subject Re: Protect syscache from bloating with negative cache entries
Date
Msg-id 20190123.173502.237450969.horiguchi.kyotaro@lab.ntt.co.jp
Whole thread Raw
In response to Re: Protect syscache from bloating with negative cache entries  (Kyotaro HORIGUCHI <horiguchi.kyotaro@lab.ntt.co.jp>)
Responses Re: Protect syscache from bloating with negative cache entries  (Bruce Momjian <bruce@momjian.us>)
List pgsql-hackers
At Mon, 21 Jan 2019 17:22:55 +0900 (Tokyo Standard Time), Kyotaro HORIGUCHI <horiguchi.kyotaro@lab.ntt.co.jp> wrote in
<20190121.172255.226467552.horiguchi.kyotaro@lab.ntt.co.jp>
> An option is an additional PGPROC member and interface functions.
> 
> struct PGPROC
> {
>  ...
>  int syscahe_usage_track_interval; /* track interval, 0 to disable */
> 
> =# select syscahce_usage_track_add(<pid>, <intvl>[, <repetition>]);
> =# select syscahce_usage_track_remove(2134);
> 
> 
> Or, just provide an one-shot triggering function.
> 
> =# select syscahce_take_usage_track(<pid>);
> 
> This can use both a similar PGPROC variable or SendProcSignal()
> but the former doesn't fire while idle time unless using timer.

The attached is revised version of this patchset, where the third
patch is the remote setting feature. It uses static shared memory.

=# select pg_backend_catcache_stats(<pid>, <millis>);

Activates or changes catcache stats feature on the backend with
PID. (The name should be changed to .._syscache_stats, though.)
It is far smaller than the remote-GUC feature. (It contains a
part that should be in the previous patch. I will fix it later.)


regards.

-- 
Kyotaro Horiguchi
NTT Open Source Software Center
From 067f8ad60f259453271d2bf8323505beb5b9e0a9 Mon Sep 17 00:00:00 2001
From: Kyotaro Horiguchi <horiguchi.kyotaro@lab.ntt.co.jp>
Date: Tue, 16 Oct 2018 13:04:30 +0900
Subject: [PATCH 1/3] Remove entries that haven't been used for a certain time

Catcache entries can be left alone for several reasons. It is not
desirable that they eat up memory. With this patch, This adds
consideration of removal of entries that haven't been used for a
certain time before enlarging the hash array.
---
 doc/src/sgml/config.sgml                      |  38 ++++++
 src/backend/access/transam/xact.c             |   5 +
 src/backend/utils/cache/catcache.c            | 166 ++++++++++++++++++++++++--
 src/backend/utils/misc/guc.c                  |  23 ++++
 src/backend/utils/misc/postgresql.conf.sample |   2 +
 src/include/utils/catcache.h                  |  28 ++++-
 6 files changed, 254 insertions(+), 8 deletions(-)

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index b6f5822b84..af3c52b868 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -1662,6 +1662,44 @@ include_dir 'conf.d'
       </listitem>
      </varlistentry>
 
+     <varlistentry id="guc-syscache-memory-target" xreflabel="syscache_memory_target">
+      <term><varname>syscache_memory_target</varname> (<type>integer</type>)
+      <indexterm>
+       <primary><varname>syscache_memory_target</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        Specifies the maximum amount of memory to which syscache is expanded
+        without pruning. The value defaults to 0, indicating that pruning is
+        always considered. After exceeding this size, syscache pruning is
+        considered according to
+        <xref linkend="guc-syscache-prune-min-age"/>. If you need to keep
+        certain amount of syscache entries with intermittent usage, try
+        increase this setting.
+       </para>
+      </listitem>
+     </varlistentry>
+
+     <varlistentry id="guc-syscache-prune-min-age" xreflabel="syscache_prune_min_age">
+      <term><varname>syscache_prune_min_age</varname> (<type>integer</type>)
+      <indexterm>
+       <primary><varname>syscache_prune_min_age</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        Specifies the minimum amount of unused time in seconds at which a
+        syscache entry is considered to be removed. -1 indicates that syscache
+        pruning is disabled at all. The value defaults to 600 seconds
+        (<literal>10 minutes</literal>). The syscache entries that are not
+        used for the duration can be removed to prevent syscache bloat. This
+        behavior is suppressed until the size of syscache exceeds
+        <xref linkend="guc-syscache-memory-target"/>.
+       </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/access/transam/xact.c b/src/backend/access/transam/xact.c
index 18467d96d2..dbffec8067 100644
--- a/src/backend/access/transam/xact.c
+++ b/src/backend/access/transam/xact.c
@@ -733,7 +733,12 @@ void
 SetCurrentStatementStartTimestamp(void)
 {
     if (!IsParallelWorker())
+    {
         stmtStartTimestamp = GetCurrentTimestamp();
+
+        /* Set this timestamp as aproximated current time */
+        SetCatCacheClock(stmtStartTimestamp);
+    }
     else
         Assert(stmtStartTimestamp != 0);
 }
diff --git a/src/backend/utils/cache/catcache.c b/src/backend/utils/cache/catcache.c
index 8152f7e21e..ee40093553 100644
--- a/src/backend/utils/cache/catcache.c
+++ b/src/backend/utils/cache/catcache.c
@@ -72,9 +72,24 @@
 #define CACHE6_elog(a,b,c,d,e,f,g)
 #endif
 
+/*
+ * GUC variable to define the minimum size of hash to cosider entry eviction.
+ * This variable is shared among various cache mechanisms.
+ */
+int cache_memory_target = 0;
+
+/* GUC variable to define the minimum age of entries that will be cosidered to
+ * be evicted in seconds. This variable is shared among various cache
+ * mechanisms.
+ */
+int cache_prune_min_age = 600;
+
 /* Cache management header --- pointer is NULL until created */
 static CatCacheHeader *CacheHdr = NULL;
 
+/* Timestamp used for any operation on caches. */
+TimestampTz    catcacheclock = 0;
+
 static inline HeapTuple SearchCatCacheInternal(CatCache *cache,
                        int nkeys,
                        Datum v1, Datum v2,
@@ -491,6 +506,7 @@ CatCacheRemoveCTup(CatCache *cache, CatCTup *ct)
         CatCacheFreeKeys(cache->cc_tupdesc, cache->cc_nkeys,
                          cache->cc_keyno, ct->keys);
 
+    cache->cc_tupsize -= ct->size;
     pfree(ct);
 
     --cache->cc_ntup;
@@ -842,6 +858,7 @@ InitCatCache(int id,
     cp->cc_nkeys = nkeys;
     for (i = 0; i < nkeys; ++i)
         cp->cc_keyno[i] = key[i];
+    cp->cc_tupsize = 0;
 
     /*
      * new cache is initialized as far as we can go for now. print some
@@ -859,9 +876,129 @@ InitCatCache(int id,
      */
     MemoryContextSwitchTo(oldcxt);
 
+    /* initilize catcache reference clock if haven't done yet */
+    if (catcacheclock == 0)
+        catcacheclock = GetCurrentTimestamp();
+
     return cp;
 }
 
+/*
+ * CatCacheCleanupOldEntries - Remove infrequently-used entries
+ *
+ * Catcache entries can be left alone for several reasons. We remove them if
+ * they are not accessed for a certain time to prevent catcache from
+ * bloating. The eviction is performed with the similar algorithm with buffer
+ * eviction using access counter. Entries that are accessed several times can
+ * live longer than those that have had no access in the same duration.
+ */
+static bool
+CatCacheCleanupOldEntries(CatCache *cp)
+{
+    int            i;
+    int            nremoved = 0;
+    size_t        hash_size;
+#ifdef CATCACHE_STATS
+    /* These variables are only for debugging purpose */
+    int            ntotal = 0;
+    /*
+     * nth element in nentries stores the number of cache entries that have
+     * lived unaccessed for corresponding multiple in ageclass of
+     * cache_prune_min_age. The index of nremoved_entry is the value of the
+     * clock-sweep counter, which takes from 0 up to 2.
+     */
+    double        ageclass[] = {0.05, 0.1, 1.0, 2.0, 3.0, 0.0};
+    int            nentries[] = {0, 0, 0, 0, 0, 0};
+    int            nremoved_entry[3] = {0, 0, 0};
+    int            j;
+#endif
+
+    /* Return immediately if no pruning is wanted */
+    if (cache_prune_min_age < 0)
+        return false;
+
+    /*
+     * Return without pruning if the size of the hash is below the target.
+     */
+    hash_size = cp->cc_nbuckets * sizeof(dlist_head);
+    if (hash_size + cp->cc_tupsize < (Size) cache_memory_target * 1024L)
+        return false;
+    
+    /* Search the whole hash for 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;
+
+
+            /*
+             * Calculate the duration from the time of the last access to the
+             * "current" time. Since catcacheclock is not advanced within a
+             * transaction, the entries that are accessed within the current
+             * transaction won't be pruned.
+             */
+            TimestampDifference(ct->lastaccess, catcacheclock, &entry_age, &us);
+
+#ifdef CATCACHE_STATS
+            /* count catcache entries for each age class */
+            ntotal++;
+            for (j = 0 ;
+                 ageclass[j] != 0.0 &&
+                     entry_age > cache_prune_min_age * ageclass[j] ;
+                 j++);
+            if (ageclass[j] == 0.0) j--;
+            nentries[j]++;
+#endif
+
+            /*
+             * Try to remove entries older than cache_prune_min_age seconds.
+             * Entries that are not accessed after last pruning are removed in
+             * that seconds, and that has been accessed several times are
+             * removed after leaving alone for up to three times of the
+             * duration. We don't try shrink buckets since pruning effectively
+             * caps catcache expansion in the long term.
+             */
+            if (entry_age > cache_prune_min_age)
+            {
+#ifdef CATCACHE_STATS
+                Assert (ct->naccess >= 0 && ct->naccess <= 2);
+                nremoved_entry[ct->naccess]++;
+#endif
+                if (ct->naccess > 0)
+                    ct->naccess--;
+                else
+                {
+                    if (!ct->c_list || ct->c_list->refcount == 0)
+                    {
+                        CatCacheRemoveCTup(cp, ct);
+                        nremoved++;
+                    }
+                }
+            }
+        }
+    }
+
+#ifdef CATCACHE_STATS
+    ereport(DEBUG1,
+            (errmsg ("removed %d/%d, age(-%.0fs:%d, -%.0fs:%d, *-%.0fs:%d, -%.0fs:%d, -%.0fs:%d) naccessed(0:%d, 1:%d,
2:%d)",
+                     nremoved, ntotal,
+                     ageclass[0] * cache_prune_min_age, nentries[0],
+                     ageclass[1] * cache_prune_min_age, nentries[1],
+                     ageclass[2] * cache_prune_min_age, nentries[2],
+                     ageclass[3] * cache_prune_min_age, nentries[3],
+                     ageclass[4] * cache_prune_min_age, nentries[4],
+                     nremoved_entry[0], nremoved_entry[1], nremoved_entry[2]),
+             errhidestmt(true)));
+#endif
+
+    return nremoved > 0;
+}
+
 /*
  * Enlarge a catcache, doubling the number of buckets.
  */
@@ -1275,6 +1412,11 @@ SearchCatCacheInternal(CatCache *cache,
          */
         dlist_move_head(bucket, &ct->cache_elem);
 
+        /* Update access information for pruning */
+        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.
@@ -1820,11 +1962,13 @@ CatalogCacheCreateEntry(CatCache *cache, HeapTuple ntp, Datum *arguments,
     CatCTup    *ct;
     HeapTuple    dtp;
     MemoryContext oldcxt;
+    int            tupsize = 0;
 
     /* negative entries have no tuple associated */
     if (ntp)
     {
         int            i;
+        int            tupsize;
 
         Assert(!negative);
 
@@ -1843,13 +1987,14 @@ CatalogCacheCreateEntry(CatCache *cache, HeapTuple ntp, Datum *arguments,
         /* Allocate memory for CatCTup and the cached tuple in one go */
         oldcxt = MemoryContextSwitchTo(CacheMemoryContext);
 
-        ct = (CatCTup *) palloc(sizeof(CatCTup) +
-                                MAXIMUM_ALIGNOF + dtp->t_len);
+        tupsize = sizeof(CatCTup) +    MAXIMUM_ALIGNOF + dtp->t_len;
+        ct = (CatCTup *) palloc(tupsize);
         ct->tuple.t_len = dtp->t_len;
         ct->tuple.t_self = dtp->t_self;
         ct->tuple.t_tableOid = dtp->t_tableOid;
         ct->tuple.t_data = (HeapTupleHeader)
             MAXALIGN(((char *) ct) + sizeof(CatCTup));
+        ct->size = tupsize;
         /* copy tuple contents */
         memcpy((char *) ct->tuple.t_data,
                (const char *) dtp->t_data,
@@ -1877,8 +2022,8 @@ CatalogCacheCreateEntry(CatCache *cache, HeapTuple ntp, Datum *arguments,
     {
         Assert(negative);
         oldcxt = MemoryContextSwitchTo(CacheMemoryContext);
-        ct = (CatCTup *) palloc(sizeof(CatCTup));
-
+        tupsize = sizeof(CatCTup);
+        ct = (CatCTup *) palloc(tupsize);
         /*
          * Store keys - they'll point into separately allocated memory if not
          * by-value.
@@ -1899,17 +2044,24 @@ CatalogCacheCreateEntry(CatCache *cache, HeapTuple ntp, Datum *arguments,
     ct->dead = false;
     ct->negative = negative;
     ct->hash_value = hashValue;
+    ct->naccess = 0;
+    ct->lastaccess = catcacheclock;
+    ct->size = tupsize;
 
     dlist_push_head(&cache->cc_bucket[hashIndex], &ct->cache_elem);
 
     cache->cc_ntup++;
     CacheHdr->ch_ntup++;
+    cache->cc_tupsize += tupsize;
 
     /*
-     * 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 cleanup by removing
+     * infrequently used entries to make a room for the new entry. If it
+     * 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);
 
     return ct;
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index c216ed0922..134c357bf3 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -80,6 +80,7 @@
 #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"
@@ -2190,6 +2191,28 @@ static struct config_int ConfigureNamesInt[] =
         NULL, NULL, NULL
     },
 
+    {
+        {"cache_memory_target", PGC_USERSET, RESOURCES_MEM,
+            gettext_noop("Sets the minimum syscache size to keep."),
+            gettext_noop("Cache is not pruned before exceeding this size."),
+            GUC_UNIT_KB
+        },
+        &cache_memory_target,
+        0, 0, MAX_KILOBYTES,
+        NULL, NULL, NULL
+    },
+
+    {
+        {"cache_prune_min_age", PGC_USERSET, RESOURCES_MEM,
+            gettext_noop("Sets the minimum unused duration of cache entries before removal."),
+            gettext_noop("Cache entries that live unused for longer than this seconds are considered to be
removed."),
+            GUC_UNIT_S
+        },
+        &cache_prune_min_age,
+        600, -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 a21865a77f..d82af3bd6c 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -128,6 +128,8 @@
 #work_mem = 4MB                # min 64kB
 #maintenance_work_mem = 64MB        # min 1MB
 #autovacuum_work_mem = -1        # min 1MB, or -1 to use maintenance_work_mem
+#cache_memory_target = 0kB    # in kB
+#cache_prune_min_age = 600s    # -1 disables pruning
 #max_stack_depth = 2MB            # min 100kB
 #dynamic_shared_memory_type = posix    # 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..5d24809900 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"
 
@@ -61,6 +62,7 @@ typedef struct catcache
     slist_node    cc_next;        /* list link */
     ScanKeyData cc_skey[CATCACHE_MAXKEYS];    /* precomputed key info for heap
                                              * scans */
+    int            cc_tupsize;        /* total amount of catcache tuples */
 
     /*
      * Keep these at the end, so that compiling catcache.c with CATCACHE_STATS
@@ -119,7 +121,9 @@ 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;        /* approx. timestamp of the last usage */
+    int            size;            /* palloc'ed size off this tuple */
     /*
      * The tuple may also be a member of at most one CatCList.  (If a single
      * catcache is list-searched with varying numbers of keys, we may have to
@@ -189,6 +193,28 @@ typedef struct catcacheheader
 /* this extern duplicates utils/memutils.h... */
 extern PGDLLIMPORT MemoryContext CacheMemoryContext;
 
+/* for guc.c, not PGDLLPMPORT'ed */
+extern int cache_prune_min_age;
+extern int cache_memory_target;
+
+/* to use as access timestamp of catcache entries */
+extern TimestampTz catcacheclock;
+
+/*
+ * SetCatCacheClock - set timestamp for catcache access record
+ */
+static inline void
+SetCatCacheClock(TimestampTz ts)
+{
+    catcacheclock = ts;
+}
+
+static inline TimestampTz
+GetCatCacheClock(void)
+{
+    return catcacheclock;
+}
+
 extern void CreateCacheMemoryContext(void);
 
 extern CatCache *InitCatCache(int id, Oid reloid, Oid indexoid,
-- 
2.16.3

From f595a8a03f4438c52303c7fae3d95492550106b5 Mon Sep 17 00:00:00 2001
From: Kyotaro Horiguchi <horiguchi.kyotaro@lab.ntt.co.jp>
Date: Tue, 16 Oct 2018 15:48:28 +0900
Subject: [PATCH 2/3] Syscache usage tracking feature.

Collects syscache usage statictics and show it using the view
pg_stat_syscache. The feature is controlled by the GUC variable
track_syscache_usage_interval.
---
 doc/src/sgml/config.sgml                      |  15 ++
 src/backend/catalog/system_views.sql          |  17 +++
 src/backend/postmaster/pgstat.c               | 201 ++++++++++++++++++++++++--
 src/backend/tcop/postgres.c                   |  23 +++
 src/backend/utils/adt/pgstatfuncs.c           | 134 +++++++++++++++++
 src/backend/utils/cache/catcache.c            | 115 +++++++++++----
 src/backend/utils/cache/syscache.c            |  24 +++
 src/backend/utils/init/globals.c              |   1 +
 src/backend/utils/init/postinit.c             |  11 ++
 src/backend/utils/misc/guc.c                  |  10 ++
 src/backend/utils/misc/postgresql.conf.sample |   1 +
 src/include/catalog/pg_proc.dat               |   9 ++
 src/include/miscadmin.h                       |   1 +
 src/include/pgstat.h                          |   6 +-
 src/include/utils/catcache.h                  |   9 +-
 src/include/utils/syscache.h                  |  19 +++
 src/include/utils/timeout.h                   |   1 +
 src/test/regress/expected/rules.out           |  24 ++-
 18 files changed, 576 insertions(+), 45 deletions(-)

diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index af3c52b868..6dd024340b 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -6662,6 +6662,21 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv;
       </listitem>
      </varlistentry>
 
+     <varlistentry id="guc-track-syscache-usage-interval" xreflabel="track_syscache_usage_interval">
+      <term><varname>track_syscache_usage_interval</varname> (<type>integer</type>)
+      <indexterm>
+       <primary><varname>track_syscache_usage_interval</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        Specifies the interval to collect system cache usage statistics in
+        milliseconds. This parameter is 0 by default, which means disabled.
+        Only superusers can change this setting.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="guc-track-io-timing" xreflabel="track_io_timing">
       <term><varname>track_io_timing</varname> (<type>boolean</type>)
       <indexterm>
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index f4d9e9daf7..30e2da935a 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -904,6 +904,22 @@ CREATE VIEW pg_stat_progress_vacuum AS
     FROM pg_stat_get_progress_info('VACUUM') AS S
         LEFT JOIN pg_database D ON S.datid = D.oid;
 
+CREATE VIEW pg_stat_syscache AS
+    SELECT
+        S.pid                AS pid,
+        S.relid::regclass    AS relname,
+        S.indid::regclass    AS cache_name,
+        S.size                AS size,
+        S.ntup                AS ntuples,
+        S.searches            AS searches,
+        S.hits                AS hits,
+        S.neg_hits            AS neg_hits,
+        S.ageclass            AS ageclass,
+        S.last_update        AS last_update
+    FROM pg_stat_activity A
+    JOIN LATERAL (SELECT A.pid, * FROM pg_get_syscache_stats(A.pid)) S
+        ON (A.pid = S.pid);
+
 CREATE VIEW pg_user_mappings AS
     SELECT
         U.oid       AS umid,
@@ -1183,6 +1199,7 @@ GRANT EXECUTE ON FUNCTION pg_ls_waldir() TO pg_monitor;
 GRANT EXECUTE ON FUNCTION pg_ls_archive_statusdir() TO pg_monitor;
 GRANT EXECUTE ON FUNCTION pg_ls_tmpdir() TO pg_monitor;
 GRANT EXECUTE ON FUNCTION pg_ls_tmpdir(oid) TO pg_monitor;
+GRANT EXECUTE ON FUNCTION pg_get_syscache_stats(int) TO pg_monitor;
 
 GRANT pg_read_all_settings TO pg_monitor;
 GRANT pg_read_all_stats TO pg_monitor;
diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
index 13da412c59..2e8b7d0d91 100644
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -66,6 +66,7 @@
 #include "utils/ps_status.h"
 #include "utils/rel.h"
 #include "utils/snapmgr.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 #include "utils/tqual.h"
 
@@ -125,6 +126,7 @@
 bool        pgstat_track_activities = false;
 bool        pgstat_track_counts = false;
 int            pgstat_track_functions = TRACK_FUNC_OFF;
+int            pgstat_track_syscache_usage_interval = 0;
 int            pgstat_track_activity_query_size = 1024;
 
 /* ----------
@@ -237,6 +239,11 @@ typedef struct TwoPhasePgStatRecord
     bool        t_truncated;    /* was the relation truncated? */
 } TwoPhasePgStatRecord;
 
+/* bitmap symbols to specify target file types remove */
+#define PGSTAT_REMFILE_DBSTAT    1        /* remove only databsae stats files */
+#define PGSTAT_REMFILE_SYSCACHE    2        /* remove only syscache stats files */
+#define PGSTAT_REMFILE_ALL        3        /* remove both type of files */
+
 /*
  * Info about current "snapshot" of stats file
  */
@@ -336,6 +343,7 @@ static void pgstat_recv_funcpurge(PgStat_MsgFuncpurge *msg, int len);
 static void pgstat_recv_recoveryconflict(PgStat_MsgRecoveryConflict *msg, int len);
 static void pgstat_recv_deadlock(PgStat_MsgDeadlock *msg, int len);
 static void pgstat_recv_tempfile(PgStat_MsgTempFile *msg, int len);
+static void pgstat_syscache_remove_statsfile(void);
 
 /* ------------------------------------------------------------
  * Public functions called from postmaster follow
@@ -631,10 +639,13 @@ startup_failed:
 }
 
 /*
- * subroutine for pgstat_reset_all
+ * remove stats files
+ *
+ * clean up stats files in specified directory. target is one of
+ * PGSTAT_REFILE_DBSTAT/SYSCACHE/ALL and restricts files to remove.
  */
 static void
-pgstat_reset_remove_files(const char *directory)
+pgstat_reset_remove_files(const char *directory, int target)
 {
     DIR           *dir;
     struct dirent *entry;
@@ -645,25 +656,39 @@ pgstat_reset_remove_files(const char *directory)
     {
         int            nchars;
         Oid            tmp_oid;
+        int            filetype = 0;
 
         /*
          * Skip directory entries that don't match the file names we write.
          * See get_dbstat_filename for the database-specific pattern.
          */
         if (strncmp(entry->d_name, "global.", 7) == 0)
+        {
+            filetype = PGSTAT_REMFILE_DBSTAT;
             nchars = 7;
+        }
         else
         {
+            char head[2];
+            
             nchars = 0;
-            (void) sscanf(entry->d_name, "db_%u.%n",
-                          &tmp_oid, &nchars);
-            if (nchars <= 0)
-                continue;
+            (void) sscanf(entry->d_name, "%c%c_%u.%n",
+                          head, head + 1, &tmp_oid, &nchars);
+
             /* %u allows leading whitespace, so reject that */
-            if (strchr("0123456789", entry->d_name[3]) == NULL)
+            if (nchars < 3 || !isdigit(entry->d_name[3]))
                 continue;
+
+            if  (strncmp(head, "db", 2) == 0)
+                filetype = PGSTAT_REMFILE_DBSTAT;
+            else if (strncmp(head, "cc", 2) == 0)
+                filetype = PGSTAT_REMFILE_SYSCACHE;
         }
 
+        /* skip if this is not a target */
+        if ((filetype & target) == 0)
+            continue;
+
         if (strcmp(entry->d_name + nchars, "tmp") != 0 &&
             strcmp(entry->d_name + nchars, "stat") != 0)
             continue;
@@ -684,8 +709,9 @@ pgstat_reset_remove_files(const char *directory)
 void
 pgstat_reset_all(void)
 {
-    pgstat_reset_remove_files(pgstat_stat_directory);
-    pgstat_reset_remove_files(PGSTAT_STAT_PERMANENT_DIRECTORY);
+    pgstat_reset_remove_files(pgstat_stat_directory, PGSTAT_REMFILE_ALL);
+    pgstat_reset_remove_files(PGSTAT_STAT_PERMANENT_DIRECTORY,
+                              PGSTAT_REMFILE_ALL);
 }
 
 #ifdef EXEC_BACKEND
@@ -2962,6 +2988,10 @@ pgstat_beshutdown_hook(int code, Datum arg)
     if (OidIsValid(MyDatabaseId))
         pgstat_report_stat(true);
 
+    /* clear syscache statistics files and temprary settings */
+    if (MyBackendId != InvalidBackendId)
+        pgstat_syscache_remove_statsfile();
+
     /*
      * Clear my status entry, following the protocol of bumping st_changecount
      * before and after.  We use a volatile pointer here to ensure the
@@ -4286,6 +4316,9 @@ PgstatCollectorMain(int argc, char *argv[])
     pgStatRunningInCollector = true;
     pgStatDBHash = pgstat_read_statsfiles(InvalidOid, true, true);
 
+    /* Remove left-over syscache stats files */
+    pgstat_reset_remove_files(pgstat_stat_directory, PGSTAT_REMFILE_SYSCACHE);
+
     /*
      * Loop to process messages until we get SIGQUIT or detect ungraceful
      * death of our parent postmaster.
@@ -6376,3 +6409,153 @@ pgstat_clip_activity(const char *raw_activity)
 
     return activity;
 }
+
+/*
+ * return the filename for a syscache stat file; filename is the output
+ * buffer, of length len.
+ */
+void
+pgstat_get_syscachestat_filename(bool permanent, bool tempname, int backendid,
+                                 char *filename, int len)
+{
+    int            printed;
+
+    /* NB -- pgstat_reset_remove_files knows about the pattern this uses */
+    printed = snprintf(filename, len, "%s/cc_%u.%s",
+                       permanent ? PGSTAT_STAT_PERMANENT_DIRECTORY :
+                       pgstat_stat_directory,
+                       backendid,
+                       tempname ? "tmp" : "stat");
+    if (printed >= len)
+        elog(ERROR, "overlength pgstat path");
+}
+
+/* removes syscache stats files of this backend */
+static void
+pgstat_syscache_remove_statsfile(void)
+{
+    char    fname[MAXPGPATH];
+
+    pgstat_get_syscachestat_filename(false, false, MyBackendId,
+                                     fname, MAXPGPATH);
+    unlink(fname);        /* don't care of the result */
+}
+
+/*
+ * pgstat_write_syscache_stats() -
+ *        Write the syscache statistics files.
+ *
+ * If 'force' is false, this function skips writing a file and resturns the
+ * time remaining in the current interval in milliseconds. If'force' is true,
+ * writes a file regardless of the remaining time and reset the interval.
+ */
+long
+pgstat_write_syscache_stats(bool force)
+{
+    static TimestampTz last_report = 0;
+    TimestampTz now;
+    long elapsed;
+    long secs;
+    int     usecs;
+    int    cacheId;
+    FILE    *fpout;
+    char    statfile[MAXPGPATH];
+    char    tmpfile[MAXPGPATH];
+
+    /* Return if we don't want it */
+    if (!force && pgstat_track_syscache_usage_interval <= 0)
+    {
+        /* disabled. remove the statistics file if any */
+        if (last_report > 0)
+        {
+            last_report = 0;
+            pgstat_syscache_remove_statsfile();
+        }
+        return 0;
+    }
+    
+    /* Check aginst the interval */
+    now = GetCurrentTransactionStopTimestamp();
+    TimestampDifference(last_report, now, &secs, &usecs);
+    elapsed = secs * 1000 + usecs / 1000;
+
+    if (!force && elapsed < pgstat_track_syscache_usage_interval)
+    {
+        /* not yet the time, inform the remaining time to the caller */
+        return pgstat_track_syscache_usage_interval - elapsed;
+    }
+
+    /* now update the stats */
+    last_report = now;
+
+    pgstat_get_syscachestat_filename(false, true,
+                                     MyBackendId, tmpfile, MAXPGPATH);
+    pgstat_get_syscachestat_filename(false, false,
+                                     MyBackendId, statfile, MAXPGPATH);
+
+    /*
+     * This function can be called from ProcessInterrupts(). Inhibit recursive
+     * interrupts to avoid recursive entry.
+     */
+    HOLD_INTERRUPTS();
+
+    fpout = AllocateFile(tmpfile, PG_BINARY_W);
+    if (fpout == NULL)
+    {
+        ereport(LOG,
+                (errcode_for_file_access(),
+                 errmsg("could not open temporary statistics file \"%s\": %m",
+                        tmpfile)));
+        /*
+         * Failure writing this file is not critical. Just skip this time and
+         * tell caller to wait for the next interval.
+         */
+        RESUME_INTERRUPTS();
+        return pgstat_track_syscache_usage_interval;
+    }
+
+    /* write out every catcache stats */
+    for (cacheId = 0 ; cacheId < SysCacheSize ; cacheId++)
+    {
+        SysCacheStats *stats;
+        
+        stats = SysCacheGetStats(cacheId);
+        Assert (stats);
+
+        /* write error is checked later using ferror() */
+        fputc('T', fpout);
+        (void)fwrite(&cacheId, sizeof(int), 1, fpout);
+        (void)fwrite(&last_report, sizeof(TimestampTz), 1, fpout);
+        (void)fwrite(stats, sizeof(*stats), 1, fpout);
+    }
+    fputc('E', fpout);
+
+    if (ferror(fpout))
+    {
+        ereport(LOG,
+                (errcode_for_file_access(),
+                 errmsg("could not write syscache statistics file \"%s\": %m",
+                        tmpfile)));
+        FreeFile(fpout);
+        unlink(tmpfile);
+    }
+    else if (FreeFile(fpout) < 0)
+    {
+        ereport(LOG,
+                (errcode_for_file_access(),
+                 errmsg("could not close syscache statistics file \"%s\": %m",
+                        tmpfile)));
+        unlink(tmpfile);
+    }
+    else if (rename(tmpfile, statfile) < 0)
+    {
+        ereport(LOG,
+                (errcode_for_file_access(),
+                 errmsg("could not rename syscache statistics file \"%s\" to \"%s\": %m",
+                        tmpfile, statfile)));
+        unlink(tmpfile);
+    }
+
+    RESUME_INTERRUPTS();
+    return 0;
+}
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index 0c0891b33e..e7972e645f 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -3157,6 +3157,12 @@ ProcessInterrupts(void)
 
     }
 
+    if (IdleSyscacheStatsUpdateTimeoutPending)
+    {
+        IdleSyscacheStatsUpdateTimeoutPending = false;
+        pgstat_write_syscache_stats(true);
+    }
+
     if (ParallelMessagePending)
         HandleParallelMessages();
 }
@@ -3733,6 +3739,7 @@ PostgresMain(int argc, char *argv[],
     sigjmp_buf    local_sigjmp_buf;
     volatile bool send_ready_for_query = true;
     bool        disable_idle_in_transaction_timeout = false;
+    bool        disable_idle_catcache_update_timeout = false;
 
     /* Initialize startup process environment if necessary. */
     if (!IsUnderPostmaster)
@@ -4173,9 +4180,19 @@ PostgresMain(int argc, char *argv[],
             }
             else
             {
+                long timeout;
+
                 ProcessCompletedNotifies();
                 pgstat_report_stat(false);
 
+                timeout = pgstat_write_syscache_stats(false);
+
+                if (timeout > 0)
+                {
+                    disable_idle_catcache_update_timeout = true;
+                    enable_timeout_after(IDLE_CATCACHE_UPDATE_TIMEOUT,
+                                         timeout);
+                }
                 set_ps_display("idle", false);
                 pgstat_report_activity(STATE_IDLE, NULL);
             }
@@ -4218,6 +4235,12 @@ PostgresMain(int argc, char *argv[],
             disable_idle_in_transaction_timeout = false;
         }
 
+        if (disable_idle_catcache_update_timeout)
+        {
+            disable_timeout(IDLE_CATCACHE_UPDATE_TIMEOUT, false);
+            disable_idle_catcache_update_timeout = false;
+        }
+
         /*
          * (6) check for any other interesting events that happened while we
          * slept.
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 053bb73863..0d32bf8daa 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -14,6 +14,8 @@
  */
 #include "postgres.h"
 
+#include <sys/stat.h>
+
 #include "access/htup_details.h"
 #include "catalog/pg_authid.h"
 #include "catalog/pg_type.h"
@@ -28,6 +30,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/inet.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 #define UINT32_ACCESS_ONCE(var)         ((uint32)(*((volatile uint32 *)&(var))))
@@ -1882,3 +1885,134 @@ pg_stat_get_archiver(PG_FUNCTION_ARGS)
     PG_RETURN_DATUM(HeapTupleGetDatum(
                                       heap_form_tuple(tupdesc, values, nulls)));
 }
+
+Datum
+pgstat_get_syscache_stats(PG_FUNCTION_ARGS)
+{
+#define PG_GET_SYSCACHE_SIZE 9
+    int                    pid     = PG_GETARG_INT32(0);
+    ReturnSetInfo       *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
+    TupleDesc            tupdesc;
+    Tuplestorestate    *tupstore;
+    MemoryContext        per_query_ctx;
+    MemoryContext        oldcontext;
+    PgBackendStatus       *beentry;
+    int                    beid;
+    char                fname[MAXPGPATH];
+    FILE                  *fpin;
+    char c;
+
+    if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo))
+        ereport(ERROR,
+                (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+                 errmsg("set-valued function called in context that cannot accept a set")));
+    if (!(rsinfo->allowedModes & SFRM_Materialize))
+        ereport(ERROR,
+                (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+                 errmsg("materialize mode required, but it is not " \
+                        "allowed in this context")));
+
+    /* Build a tuple descriptor for our result type */
+    if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
+        elog(ERROR, "return type must be a row type");
+    
+
+    per_query_ctx = rsinfo->econtext->ecxt_per_query_memory;
+
+    oldcontext = MemoryContextSwitchTo(per_query_ctx);
+    tupstore = tuplestore_begin_heap(true, false, work_mem);
+    rsinfo->returnMode = SFRM_Materialize;
+    rsinfo->setResult = tupstore;
+    rsinfo->setDesc = tupdesc;
+
+    MemoryContextSwitchTo(oldcontext);
+
+    /* find beentry for given pid*/
+    beentry = NULL;
+    for (beid = 1;
+         (beentry = pgstat_fetch_stat_beentry(beid)) &&
+             beentry->st_procpid != pid ;
+         beid++);
+
+    /*
+     * we silently return empty result on failure or insufficient privileges
+     */
+    if (!beentry ||
+        (!has_privs_of_role(GetUserId(), beentry->st_userid) &&
+         !is_member_of_role(GetUserId(), DEFAULT_ROLE_READ_ALL_STATS)))
+        goto no_data;
+
+    pgstat_get_syscachestat_filename(false, false, beid, fname, MAXPGPATH);
+
+    if ((fpin = AllocateFile(fname, PG_BINARY_R)) == NULL)
+    {
+        if (errno != ENOENT)
+            ereport(WARNING,
+                    (errcode_for_file_access(),
+                     errmsg("could not open statistics file \"%s\": %m",
+                            fname)));
+        /* also return empty on no statistics file */
+        goto no_data;
+    }
+
+    /* read the statistics file into tuplestore */
+    while ((c = fgetc(fpin)) == 'T')
+    {
+        TimestampTz last_update;
+        SysCacheStats stats;
+        int cacheid;
+        Datum values[PG_GET_SYSCACHE_SIZE];
+        bool nulls[PG_GET_SYSCACHE_SIZE] = {0};
+        Datum datums[SYSCACHE_STATS_NAGECLASSES * 2];
+        bool arrnulls[SYSCACHE_STATS_NAGECLASSES * 2] = {0};
+        int    dims[] = {SYSCACHE_STATS_NAGECLASSES, 2};
+        int lbs[] = {1, 1};
+        ArrayType *arr;
+        int i, j;
+
+        fread(&cacheid, sizeof(int), 1, fpin);
+        fread(&last_update, sizeof(TimestampTz), 1, fpin);
+        if (fread(&stats, 1, sizeof(stats), fpin) != sizeof(stats))
+        {
+            ereport(WARNING, 
+                    (errmsg("corrupted syscache statistics file \"%s\"",
+                            fname)));
+            goto no_data;
+        }
+
+        i = 0;
+        values[i++] = ObjectIdGetDatum(stats.reloid);
+        values[i++] = ObjectIdGetDatum(stats.indoid);
+        values[i++] = Int64GetDatum(stats.size);
+        values[i++] = Int64GetDatum(stats.ntuples);
+        values[i++] = Int64GetDatum(stats.nsearches);
+        values[i++] = Int64GetDatum(stats.nhits);
+        values[i++] = Int64GetDatum(stats.nneg_hits);
+
+        for (j = 0 ; j < SYSCACHE_STATS_NAGECLASSES ; j++)
+        {
+            datums[j * 2] = Int32GetDatum((int32) stats.ageclasses[j]);
+            datums[j * 2 + 1] = Int32GetDatum((int32) stats.nclass_entries[j]);
+        }            
+
+        arr = construct_md_array(datums, arrnulls, 2, dims, lbs,
+                              INT4OID, sizeof(int32), true, 'i');
+        values[i++] = PointerGetDatum(arr);
+
+        values[i++] = TimestampTzGetDatum(last_update);
+
+        Assert (i == PG_GET_SYSCACHE_SIZE);
+
+        tuplestore_putvalues(tupstore, tupdesc, values, nulls);
+    }
+
+    /* check for the end of file. abandon the result if file is broken */
+    if (c != 'E' || fgetc(fpin) != EOF)
+        tuplestore_clear(tupstore);
+
+    FreeFile(fpin);
+
+no_data:
+    tuplestore_donestoring(tupstore);
+    return (Datum) 0;
+}
diff --git a/src/backend/utils/cache/catcache.c b/src/backend/utils/cache/catcache.c
index ee40093553..4a3b3094a0 100644
--- a/src/backend/utils/cache/catcache.c
+++ b/src/backend/utils/cache/catcache.c
@@ -90,6 +90,10 @@ static CatCacheHeader *CacheHdr = NULL;
 /* Timestamp used for any operation on caches. */
 TimestampTz    catcacheclock = 0;
 
+/* age classes for pruning */
+static double ageclass[SYSCACHE_STATS_NAGECLASSES]
+    = {0.05, 0.1, 1.0, 2.0, 3.0, 0.0};
+
 static inline HeapTuple SearchCatCacheInternal(CatCache *cache,
                        int nkeys,
                        Datum v1, Datum v2,
@@ -620,9 +624,7 @@ CatCacheInvalidate(CatCache *cache, uint32 hashValue)
             else
                 CatCacheRemoveCTup(cache, ct);
             CACHE1_elog(DEBUG2, "CatCacheInvalidate: invalidated");
-#ifdef CATCACHE_STATS
             cache->cc_invals++;
-#endif
             /* could be multiple matches, so keep looking! */
         }
     }
@@ -698,9 +700,7 @@ ResetCatalogCache(CatCache *cache)
             }
             else
                 CatCacheRemoveCTup(cache, ct);
-#ifdef CATCACHE_STATS
             cache->cc_invals++;
-#endif
         }
     }
 }
@@ -907,10 +907,11 @@ CatCacheCleanupOldEntries(CatCache *cp)
      * cache_prune_min_age. The index of nremoved_entry is the value of the
      * clock-sweep counter, which takes from 0 up to 2.
      */
-    double        ageclass[] = {0.05, 0.1, 1.0, 2.0, 3.0, 0.0};
-    int            nentries[] = {0, 0, 0, 0, 0, 0};
+    int            nentries[SYSCACHE_STATS_NAGECLASSES] = {0, 0, 0, 0, 0, 0};
     int            nremoved_entry[3] = {0, 0, 0};
     int            j;
+
+    Assert(ageclass[SYSCACHE_STATS_NAGECLASSES - 1] == 0.0);
 #endif
 
     /* Return immediately if no pruning is wanted */
@@ -924,7 +925,11 @@ CatCacheCleanupOldEntries(CatCache *cp)
     if (hash_size + cp->cc_tupsize < (Size) cache_memory_target * 1024L)
         return false;
     
-    /* Search the whole hash for entries to remove */
+    /*
+     * Search the whole hash for entries to remove. This is a quite time
+     * consuming task during catcache lookup, but accetable since now we are
+     * going to expand the hash table.
+     */
     for (i = 0; i < cp->cc_nbuckets; i++)
     {
         dlist_mutable_iter iter;
@@ -937,21 +942,21 @@ CatCacheCleanupOldEntries(CatCache *cp)
 
 
             /*
-             * Calculate the duration from the time of the last access to the
-             * "current" time. Since catcacheclock is not advanced within a
-             * transaction, the entries that are accessed within the current
-             * transaction won't be pruned.
+             * Calculate the duration from the time from the last access to
+             * the "current" time. Since catcacheclock is not advanced within
+             * a transaction, the entries that are accessed within the current
+             * transaction always get 0 as the result.
              */
             TimestampDifference(ct->lastaccess, catcacheclock, &entry_age, &us);
 
 #ifdef CATCACHE_STATS
             /* count catcache entries for each age class */
             ntotal++;
-            for (j = 0 ;
-                 ageclass[j] != 0.0 &&
-                     entry_age > cache_prune_min_age * ageclass[j] ;
-                 j++);
-            if (ageclass[j] == 0.0) j--;
+
+            j = 0;
+            while (j < SYSCACHE_STATS_NAGECLASSES - 1 &&
+                   entry_age > cache_prune_min_age * ageclass[j])
+                j++;
             nentries[j]++;
 #endif
 
@@ -984,14 +989,17 @@ CatCacheCleanupOldEntries(CatCache *cp)
     }
 
 #ifdef CATCACHE_STATS
+    StaticAssertStmt(SYSCACHE_STATS_NAGECLASSES == 6,
+                     "number of syscache age class must be 6");
     ereport(DEBUG1,
-            (errmsg ("removed %d/%d, age(-%.0fs:%d, -%.0fs:%d, *-%.0fs:%d, -%.0fs:%d, -%.0fs:%d) naccessed(0:%d, 1:%d,
2:%d)",
+            (errmsg ("removed %d/%d, age(-%.0fs:%d, -%.0fs:%d, *-%.0fs:%d, -%.0fs:%d, -%.0fs:%d, rest:%d)
naccessed(0:%d,1:%d, 2:%d)",
 
                      nremoved, ntotal,
                      ageclass[0] * cache_prune_min_age, nentries[0],
                      ageclass[1] * cache_prune_min_age, nentries[1],
                      ageclass[2] * cache_prune_min_age, nentries[2],
                      ageclass[3] * cache_prune_min_age, nentries[3],
                      ageclass[4] * cache_prune_min_age, nentries[4],
+                     nentries[5],
                      nremoved_entry[0], nremoved_entry[1], nremoved_entry[2]),
              errhidestmt(true)));
 #endif
@@ -1368,9 +1376,7 @@ SearchCatCacheInternal(CatCache *cache,
     if (unlikely(cache->cc_tupdesc == NULL))
         CatalogCacheInitializeCache(cache);
 
-#ifdef CATCACHE_STATS
     cache->cc_searches++;
-#endif
 
     /* Initialize local parameter array */
     arguments[0] = v1;
@@ -1430,9 +1436,7 @@ SearchCatCacheInternal(CatCache *cache,
             CACHE3_elog(DEBUG2, "SearchCatCache(%s): found in bucket %d",
                         cache->cc_relname, hashIndex);
 
-#ifdef CATCACHE_STATS
             cache->cc_hits++;
-#endif
 
             return &ct->tuple;
         }
@@ -1441,9 +1445,7 @@ SearchCatCacheInternal(CatCache *cache,
             CACHE3_elog(DEBUG2, "SearchCatCache(%s): found neg entry in bucket %d",
                         cache->cc_relname, hashIndex);
 
-#ifdef CATCACHE_STATS
             cache->cc_neg_hits++;
-#endif
 
             return NULL;
         }
@@ -1571,9 +1573,7 @@ SearchCatCacheMiss(CatCache *cache,
     CACHE3_elog(DEBUG2, "SearchCatCache(%s): put in bucket %d",
                 cache->cc_relname, hashIndex);
 
-#ifdef CATCACHE_STATS
     cache->cc_newloads++;
-#endif
 
     return &ct->tuple;
 }
@@ -1684,9 +1684,7 @@ SearchCatCacheList(CatCache *cache,
 
     Assert(nkeys > 0 && nkeys < cache->cc_nkeys);
 
-#ifdef CATCACHE_STATS
     cache->cc_lsearches++;
-#endif
 
     /* Initialize local parameter array */
     arguments[0] = v1;
@@ -1743,9 +1741,7 @@ SearchCatCacheList(CatCache *cache,
         CACHE2_elog(DEBUG2, "SearchCatCacheList(%s): found list",
                     cache->cc_relname);
 
-#ifdef CATCACHE_STATS
         cache->cc_lhits++;
-#endif
 
         return cl;
     }
@@ -2253,3 +2249,64 @@ PrintCatCacheListLeakWarning(CatCList *list)
          list->my_cache->cc_relname, list->my_cache->id,
          list, list->refcount);
 }
+
+/*
+ * CatCacheGetStats - fill in SysCacheStats struct.
+ *
+ * This is a support routine for SysCacheGetStats, substantially fills in the
+ * result. The classification here is based on the same criteria to
+ * CatCacheCleanupOldEntries().
+ */
+void
+CatCacheGetStats(CatCache *cache, SysCacheStats *stats)
+{
+    int    i, j;
+
+    Assert(ageclass[SYSCACHE_STATS_NAGECLASSES - 1] == 0.0);
+
+    /* fill in the stats struct */
+    stats->size = cache->cc_tupsize + cache->cc_nbuckets * sizeof(dlist_head);
+    stats->ntuples = cache->cc_ntup;
+    stats->nsearches = cache->cc_searches;
+    stats->nhits = cache->cc_hits;
+    stats->nneg_hits = cache->cc_neg_hits;
+
+    /* cache_prune_min_age can be changed on-session, fill it every time */
+    for (i = 0 ; i < SYSCACHE_STATS_NAGECLASSES ; i++)
+        stats->ageclasses[i] = (int) (cache_prune_min_age * ageclass[i]);
+
+    /*
+     * nth element in nclass_entries stores the number of cache entries that
+     * have lived unaccessed for corresponding multiple in ageclass of
+     * cache_prune_min_age.
+     */
+    memset(stats->nclass_entries, 0, sizeof(int) * SYSCACHE_STATS_NAGECLASSES);
+
+    /* Scan the whole hash */
+    for (i = 0; i < cache->cc_nbuckets; i++)
+    {
+        dlist_mutable_iter iter;
+
+        dlist_foreach_modify(iter, &cache->cc_bucket[i])
+        {
+            CatCTup    *ct = dlist_container(CatCTup, cache_elem, iter.cur);
+            long entry_age;
+            int us;
+
+            /*
+             * Calculate the duration from the time from the last access to
+             * the "current" time. Since catcacheclock is not advanced within
+             * a transaction, the entries that are accessed within the current
+             * transaction won't be pruned.
+             */
+            TimestampDifference(ct->lastaccess, catcacheclock, &entry_age, &us);
+
+            j = 0;
+            while (j < SYSCACHE_STATS_NAGECLASSES - 1 &&
+                   entry_age > stats->ageclasses[j])
+                j++;
+
+            stats->nclass_entries[j]++;
+        }
+    }
+}
diff --git a/src/backend/utils/cache/syscache.c b/src/backend/utils/cache/syscache.c
index ac98c19155..7b38a06708 100644
--- a/src/backend/utils/cache/syscache.c
+++ b/src/backend/utils/cache/syscache.c
@@ -20,6 +20,9 @@
  */
 #include "postgres.h"
 
+#include <sys/stat.h>
+#include <unistd.h>
+
 #include "access/htup_details.h"
 #include "access/sysattr.h"
 #include "catalog/indexing.h"
@@ -1534,6 +1537,27 @@ RelationSupportsSysCache(Oid relid)
     return false;
 }
 
+/*
+ * SysCacheGetStats - returns stats of specified syscache
+ *
+ * This routine returns the address of its local static memory.
+ */
+SysCacheStats *
+SysCacheGetStats(int cacheId)
+{
+    static SysCacheStats stats;
+
+    Assert(cacheId >=0 && cacheId < SysCacheSize);
+
+    memset(&stats, 0, sizeof(stats));
+
+    stats.reloid = cacheinfo[cacheId].reloid;
+    stats.indoid = cacheinfo[cacheId].indoid;
+
+    CatCacheGetStats(SysCache[cacheId], &stats);
+
+    return &stats;
+}
 
 /*
  * OID comparator for pg_qsort
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index fd51934aaf..f039ecd805 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -32,6 +32,7 @@ volatile sig_atomic_t QueryCancelPending = false;
 volatile sig_atomic_t ProcDiePending = false;
 volatile sig_atomic_t ClientConnectionLost = false;
 volatile sig_atomic_t IdleInTransactionSessionTimeoutPending = false;
+volatile sig_atomic_t IdleSyscacheStatsUpdateTimeoutPending = false;
 volatile sig_atomic_t ConfigReloadPending = false;
 volatile uint32 InterruptHoldoffCount = 0;
 volatile uint32 QueryCancelHoldoffCount = 0;
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 7415c4faab..6b0fdbbd87 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -73,6 +73,7 @@ static void ShutdownPostgres(int code, Datum arg);
 static void StatementTimeoutHandler(void);
 static void LockTimeoutHandler(void);
 static void IdleInTransactionSessionTimeoutHandler(void);
+static void IdleSyscacheStatsUpdateTimeoutHandler(void);
 static bool ThereIsAtLeastOneRole(void);
 static void process_startup_options(Port *port, bool am_superuser);
 static void process_settings(Oid databaseid, Oid roleid);
@@ -629,6 +630,8 @@ InitPostgres(const char *in_dbname, Oid dboid, const char *username,
         RegisterTimeout(LOCK_TIMEOUT, LockTimeoutHandler);
         RegisterTimeout(IDLE_IN_TRANSACTION_SESSION_TIMEOUT,
                         IdleInTransactionSessionTimeoutHandler);
+        RegisterTimeout(IDLE_CATCACHE_UPDATE_TIMEOUT,
+                        IdleSyscacheStatsUpdateTimeoutHandler);
     }
 
     /*
@@ -1240,6 +1243,14 @@ IdleInTransactionSessionTimeoutHandler(void)
     SetLatch(MyLatch);
 }
 
+static void
+IdleSyscacheStatsUpdateTimeoutHandler(void)
+{
+    IdleSyscacheStatsUpdateTimeoutPending = true;
+    InterruptPending = true;
+    SetLatch(MyLatch);
+}
+
 /*
  * Returns true if at least one role is defined in this database cluster.
  */
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 134c357bf3..e8d7b6998a 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -3154,6 +3154,16 @@ static struct config_int ConfigureNamesInt[] =
         NULL, NULL, NULL
     },
 
+    {
+        {"track_syscache_usage_interval", PGC_SUSET, STATS_COLLECTOR,
+            gettext_noop("Sets the interval between syscache usage collection, in milliseconds. Zero disables syscache
usagetracking."),
 
+            NULL
+        },
+        &pgstat_track_syscache_usage_interval,
+        0, 0, INT_MAX / 2,
+        NULL, NULL, NULL
+    },
+
     {
         {"gin_pending_list_limit", PGC_USERSET, CLIENT_CONN_STATEMENT,
             gettext_noop("Sets the maximum size of the pending list for GIN index."),
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index d82af3bd6c..4a6c9fceb5 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -554,6 +554,7 @@
 #track_io_timing = off
 #track_functions = none            # none, pl, all
 #track_activity_query_size = 1024    # (change requires restart)
+#track_syscache_usage_interval = 0    # zero disables tracking
 #stats_temp_directory = 'pg_stat_tmp'
 
 
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3ecc2e12c3..11fc1f3075 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -9669,6 +9669,15 @@
   proargmodes => '{o,o,o,o,o,o,o,o,o,o,o}',
   proargnames =>
'{slot_name,plugin,slot_type,datoid,temporary,active,active_pid,xmin,catalog_xmin,restart_lsn,confirmed_flush_lsn}',
   prosrc => 'pg_get_replication_slots' },
+{ oid => '3425',
+  descr => 'syscache statistics',
+  proname => 'pg_get_syscache_stats', prorows => '100', proisstrict => 'f',
+  proretset => 't', provolatile => 'v', prorettype => 'record',
+  proargtypes => 'int4',
+  proallargtypes => '{int4,oid,oid,int8,int8,int8,int8,int8,_int4,timestamptz}',
+  proargmodes => '{i,o,o,o,o,o,o,o,o,o}',
+  proargnames => '{pid,relid,indid,size,ntup,searches,hits,neg_hits,ageclass,last_update}',
+  prosrc => 'pgstat_get_syscache_stats' },
 { oid => '3786', descr => 'set up a logical replication slot',
   proname => 'pg_create_logical_replication_slot', provolatile => 'v',
   proparallel => 'u', prorettype => 'record', proargtypes => 'name name bool',
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index c9e35003a5..69b9a976f0 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -82,6 +82,7 @@ extern PGDLLIMPORT volatile sig_atomic_t InterruptPending;
 extern PGDLLIMPORT volatile sig_atomic_t QueryCancelPending;
 extern PGDLLIMPORT volatile sig_atomic_t ProcDiePending;
 extern PGDLLIMPORT volatile sig_atomic_t IdleInTransactionSessionTimeoutPending;
+extern PGDLLIMPORT volatile sig_atomic_t IdleSyscacheStatsUpdateTimeoutPending;
 extern PGDLLIMPORT volatile sig_atomic_t ConfigReloadPending;
 
 extern PGDLLIMPORT volatile sig_atomic_t ClientConnectionLost;
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 313ca5f3c3..4d0f5b8042 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -1134,6 +1134,7 @@ extern bool pgstat_track_activities;
 extern bool pgstat_track_counts;
 extern int    pgstat_track_functions;
 extern PGDLLIMPORT int pgstat_track_activity_query_size;
+extern int    pgstat_track_syscache_usage_interval;
 extern char *pgstat_stat_directory;
 extern char *pgstat_stat_tmpname;
 extern char *pgstat_stat_filename;
@@ -1218,7 +1219,8 @@ extern PgStat_BackendFunctionEntry *find_funcstat_entry(Oid func_id);
 extern void pgstat_initstats(Relation rel);
 
 extern char *pgstat_clip_activity(const char *raw_activity);
-
+extern void pgstat_get_syscachestat_filename(bool permanent,
+                    bool tempname, int backendid, char *filename, int len);
 /* ----------
  * pgstat_report_wait_start() -
  *
@@ -1353,5 +1355,5 @@ extern PgStat_StatFuncEntry *pgstat_fetch_stat_funcentry(Oid funcid);
 extern int    pgstat_fetch_stat_numbackends(void);
 extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
 extern PgStat_GlobalStats *pgstat_fetch_global(void);
-
+extern long pgstat_write_syscache_stats(bool force);
 #endif                            /* PGSTAT_H */
diff --git a/src/include/utils/catcache.h b/src/include/utils/catcache.h
index 5d24809900..4d51975920 100644
--- a/src/include/utils/catcache.h
+++ b/src/include/utils/catcache.h
@@ -65,10 +65,8 @@ typedef struct catcache
     int            cc_tupsize;        /* total amount of catcache tuples */
 
     /*
-     * Keep these at the end, so that compiling catcache.c with CATCACHE_STATS
-     * doesn't break ABI for other modules
+     * Statistics entries
      */
-#ifdef CATCACHE_STATS
     long        cc_searches;    /* total # searches against this cache */
     long        cc_hits;        /* # of matches against existing entry */
     long        cc_neg_hits;    /* # of matches against negative entry */
@@ -81,7 +79,6 @@ typedef struct catcache
     long        cc_invals;        /* # of entries invalidated from cache */
     long        cc_lsearches;    /* total # list-searches */
     long        cc_lhits;        /* # of matches against existing lists */
-#endif
 } CatCache;
 
 
@@ -254,4 +251,8 @@ extern void PrepareToInvalidateCacheTuple(Relation relation,
 extern void PrintCatCacheLeakWarning(HeapTuple tuple);
 extern void PrintCatCacheListLeakWarning(CatCList *list);
 
+/* defined in syscache.h */
+typedef struct syscachestats SysCacheStats;
+extern void CatCacheGetStats(CatCache *cache, SysCacheStats *syscachestats);
+
 #endif                            /* CATCACHE_H */
diff --git a/src/include/utils/syscache.h b/src/include/utils/syscache.h
index 95ee48954e..71b399c902 100644
--- a/src/include/utils/syscache.h
+++ b/src/include/utils/syscache.h
@@ -112,6 +112,24 @@ enum SysCacheIdentifier
 #define SysCacheSize (USERMAPPINGUSERSERVER + 1)
 };
 
+#define SYSCACHE_STATS_NAGECLASSES 6
+/* Struct for catcache tracking information */
+typedef struct syscachestats
+{
+    Oid        reloid;            /* target relation */
+    Oid        indoid;            /* index */
+    size_t    size;            /* size of the catcache */
+    int        ntuples;        /* number of tuples resides in the catcache */
+    int        nsearches;        /* number of searches */
+    int        nhits;            /* number of cache hits */
+    int        nneg_hits;        /* number of negative cache hits */
+    /* age classes in seconds */
+    int        ageclasses[SYSCACHE_STATS_NAGECLASSES];
+    /* number of tuples fall into the corresponding age class */
+    int        nclass_entries[SYSCACHE_STATS_NAGECLASSES];
+} SysCacheStats;
+
+
 extern void InitCatalogCache(void);
 extern void InitCatalogCachePhase2(void);
 
@@ -164,6 +182,7 @@ extern void SysCacheInvalidate(int cacheId, uint32 hashValue);
 extern bool RelationInvalidatesSnapshotsOnly(Oid relid);
 extern bool RelationHasSysCache(Oid relid);
 extern bool RelationSupportsSysCache(Oid relid);
+extern SysCacheStats *SysCacheGetStats(int cacheId);
 
 /*
  * The use of the macros below rather than direct calls to the corresponding
diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h
index 9244a2a7b7..0ab441a364 100644
--- a/src/include/utils/timeout.h
+++ b/src/include/utils/timeout.h
@@ -31,6 +31,7 @@ typedef enum TimeoutId
     STANDBY_TIMEOUT,
     STANDBY_LOCK_TIMEOUT,
     IDLE_IN_TRANSACTION_SESSION_TIMEOUT,
+    IDLE_CATCACHE_UPDATE_TIMEOUT,
     /* First user-definable timeout reason */
     USER_TIMEOUT,
     /* Maximum number of timeout reasons */
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index e384cd2279..1991e75e97 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1919,6 +1919,28 @@ pg_stat_sys_tables| SELECT pg_stat_all_tables.relid,
     pg_stat_all_tables.autoanalyze_count
    FROM pg_stat_all_tables
   WHERE ((pg_stat_all_tables.schemaname = ANY (ARRAY['pg_catalog'::name, 'information_schema'::name])) OR
(pg_stat_all_tables.schemaname~ '^pg_toast'::text));
 
+pg_stat_syscache| SELECT s.pid,
+    (s.relid)::regclass AS relname,
+    (s.indid)::regclass AS cache_name,
+    s.size,
+    s.ntup AS ntuples,
+    s.searches,
+    s.hits,
+    s.neg_hits,
+    s.ageclass,
+    s.last_update
+   FROM (pg_stat_activity a
+     JOIN LATERAL ( SELECT a.pid,
+            pg_get_syscache_stats.relid,
+            pg_get_syscache_stats.indid,
+            pg_get_syscache_stats.size,
+            pg_get_syscache_stats.ntup,
+            pg_get_syscache_stats.searches,
+            pg_get_syscache_stats.hits,
+            pg_get_syscache_stats.neg_hits,
+            pg_get_syscache_stats.ageclass,
+            pg_get_syscache_stats.last_update
+           FROM pg_get_syscache_stats(a.pid) pg_get_syscache_stats(relid, indid, size, ntup, searches, hits, neg_hits,
ageclass,last_update)) s ON ((a.pid = s.pid)));
 
 pg_stat_user_functions| SELECT p.oid AS funcid,
     n.nspname AS schemaname,
     p.proname AS funcname,
@@ -2350,7 +2372,7 @@ pg_settings|pg_settings_n|CREATE RULE pg_settings_n AS
     ON UPDATE TO pg_catalog.pg_settings DO INSTEAD NOTHING;
 pg_settings|pg_settings_u|CREATE RULE pg_settings_u AS
     ON UPDATE TO pg_catalog.pg_settings
-   WHERE (new.name = old.name) DO  SELECT set_config(old.name, new.setting, false) AS set_config;
+   WHERE (new.name = old.name) DO  SELECT set_config(old.name, new.setting, false, false) AS set_config;
 rtest_emp|rtest_emp_del|CREATE RULE rtest_emp_del AS
     ON DELETE TO public.rtest_emp DO  INSERT INTO rtest_emplog (ename, who, action, newsal, oldsal)
   VALUES (old.ename, CURRENT_USER, 'fired'::bpchar, '$0.00'::money, old.salary);
-- 
2.16.3

From 36f93fb3625e8f1753070d30ec81548a4dfe9eb1 Mon Sep 17 00:00:00 2001
From: Kyotaro Horiguchi <horiguchi.kyotaro@lab.ntt.co.jp>
Date: Wed, 23 Jan 2019 17:32:03 +0900
Subject: [PATCH 3/3] Remote setting feature for catcache statitics.

---
 src/backend/postmaster/pgstat.c    |  26 ++++++---
 src/backend/storage/ipc/ipci.c     |   3 +
 src/backend/utils/cache/catcache.c | 116 +++++++++++++++++++++++++++++++++++++
 src/include/catalog/pg_proc.dat    |   8 +++
 src/include/utils/catcache.h       |   6 ++
 5 files changed, 151 insertions(+), 8 deletions(-)

diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
index 2e8b7d0d91..338a407552 100644
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -62,6 +62,7 @@
 #include "storage/sinvaladt.h"
 #include "utils/ascii.h"
 #include "utils/guc.h"
+#include "utils/catcache.h"
 #include "utils/memutils.h"
 #include "utils/ps_status.h"
 #include "utils/rel.h"
@@ -343,7 +344,7 @@ static void pgstat_recv_funcpurge(PgStat_MsgFuncpurge *msg, int len);
 static void pgstat_recv_recoveryconflict(PgStat_MsgRecoveryConflict *msg, int len);
 static void pgstat_recv_deadlock(PgStat_MsgDeadlock *msg, int len);
 static void pgstat_recv_tempfile(PgStat_MsgTempFile *msg, int len);
-static void pgstat_syscache_remove_statsfile(void);
+static void pgstat_remove_syscache_statsfile(void);
 
 /* ------------------------------------------------------------
  * Public functions called from postmaster follow
@@ -2990,7 +2991,10 @@ pgstat_beshutdown_hook(int code, Datum arg)
 
     /* clear syscache statistics files and temprary settings */
     if (MyBackendId != InvalidBackendId)
-        pgstat_syscache_remove_statsfile();
+    {
+        pgstat_remove_syscache_statsfile();
+        SetCatcacheStatsParam(0);
+    }
 
     /*
      * Clear my status entry, following the protocol of bumping st_changecount
@@ -6432,7 +6436,7 @@ pgstat_get_syscachestat_filename(bool permanent, bool tempname, int backendid,
 
 /* removes syscache stats files of this backend */
 static void
-pgstat_syscache_remove_statsfile(void)
+pgstat_remove_syscache_statsfile(void)
 {
     char    fname[MAXPGPATH];
 
@@ -6461,15 +6465,21 @@ pgstat_write_syscache_stats(bool force)
     FILE    *fpout;
     char    statfile[MAXPGPATH];
     char    tmpfile[MAXPGPATH];
+    int        interval = pgstat_track_syscache_usage_interval;
+    int        interval_by_remote = GetCatcacheStatsParam();
+
+    /* remote setting overrides if any */
+    if (interval_by_remote > 0)
+        interval = interval_by_remote;
 
     /* Return if we don't want it */
-    if (!force && pgstat_track_syscache_usage_interval <= 0)
+    if (!force && interval <= 0)
     {
         /* disabled. remove the statistics file if any */
         if (last_report > 0)
         {
             last_report = 0;
-            pgstat_syscache_remove_statsfile();
+            pgstat_remove_syscache_statsfile();
         }
         return 0;
     }
@@ -6479,10 +6489,10 @@ pgstat_write_syscache_stats(bool force)
     TimestampDifference(last_report, now, &secs, &usecs);
     elapsed = secs * 1000 + usecs / 1000;
 
-    if (!force && elapsed < pgstat_track_syscache_usage_interval)
+    if (!force && elapsed < interval)
     {
         /* not yet the time, inform the remaining time to the caller */
-        return pgstat_track_syscache_usage_interval - elapsed;
+        return interval - elapsed;
     }
 
     /* now update the stats */
@@ -6511,7 +6521,7 @@ pgstat_write_syscache_stats(bool force)
          * tell caller to wait for the next interval.
          */
         RESUME_INTERRUPTS();
-        return pgstat_track_syscache_usage_interval;
+        return interval;
     }
 
     /* write out every catcache stats */
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2849e47d99..be5ee1f4ff 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -44,6 +44,7 @@
 #include "storage/procsignal.h"
 #include "storage/sinvaladt.h"
 #include "storage/spin.h"
+#include "utils/catcache.h"
 #include "utils/snapmgr.h"
 
 
@@ -148,6 +149,7 @@ CreateSharedMemoryAndSemaphores(bool makePrivate, int port)
         size = add_size(size, BTreeShmemSize());
         size = add_size(size, SyncScanShmemSize());
         size = add_size(size, AsyncShmemSize());
+        size = add_size(size, CatcacheStatsShmemSize());
 #ifdef EXEC_BACKEND
         size = add_size(size, ShmemBackendArraySize());
 #endif
@@ -267,6 +269,7 @@ CreateSharedMemoryAndSemaphores(bool makePrivate, int port)
     BTreeShmemInit();
     SyncScanShmemInit();
     AsyncShmemInit();
+    CatcacheStatsShmemInit();
 
 #ifdef EXEC_BACKEND
 
diff --git a/src/backend/utils/cache/catcache.c b/src/backend/utils/cache/catcache.c
index 4a3b3094a0..7ff8cd22ca 100644
--- a/src/backend/utils/cache/catcache.c
+++ b/src/backend/utils/cache/catcache.c
@@ -22,14 +22,17 @@
 #include "access/tuptoaster.h"
 #include "access/valid.h"
 #include "access/xact.h"
+#include "catalog/pg_authid.h"
 #include "catalog/pg_collation.h"
 #include "catalog/pg_operator.h"
 #include "catalog/pg_type.h"
 #include "miscadmin.h"
+#include "pgstat.h"
 #ifdef CATCACHE_STATS
 #include "storage/ipc.h"        /* for on_proc_exit */
 #endif
 #include "storage/lmgr.h"
+#include "storage/procarray.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
 #include "utils/fmgroids.h"
@@ -94,6 +97,17 @@ TimestampTz    catcacheclock = 0;
 static double ageclass[SYSCACHE_STATS_NAGECLASSES]
     = {0.05, 0.1, 1.0, 2.0, 3.0, 0.0};
 
+/* remote commanding facility */
+typedef struct CatcacheStatsParam
+{
+    int    interval;
+} CatcacheStatsParam;
+
+#define NumCatcacheStatsParam (MaxBackends + NUM_AUXPROCTYPES)
+
+static slock_t CatcacheStatsParamLock;
+static CatcacheStatsParam *CatcacheStatsParamArray = NULL;
+
 static inline HeapTuple SearchCatCacheInternal(CatCache *cache,
                        int nkeys,
                        Datum v1, Datum v2,
@@ -2310,3 +2324,105 @@ CatCacheGetStats(CatCache *cache, SysCacheStats *stats)
         }
     }
 }
+
+/* Report shared-memory space needed */
+Size
+CatcacheStatsShmemSize(void)
+{
+    Size size;
+
+    /* The same number of elements with backend status array */
+    size = mul_size(sizeof(CatcacheStatsParam), NumCatcacheStatsParam);
+
+    return size;
+}
+
+/* Initialize the shared parameter array for catcache statistics */
+void
+CatcacheStatsShmemInit(void)
+{
+    Size size;
+    bool found;
+
+    size = CatcacheStatsShmemSize();
+    CatcacheStatsParamArray = (CatcacheStatsParam *)
+        ShmemInitStruct("Backend Catcache Statistics Parameter Array",
+                        size, &found);
+
+    if (!found)
+    {
+        /* We're the first, initilize it */
+        MemSet(CatcacheStatsParamArray, 0, size);
+    }
+
+    SpinLockInit(&CatcacheStatsParamLock);
+}
+
+/*
+ * SQL callable function to take catcache statistics of another backend
+ */
+Datum
+backend_catcache_stats(PG_FUNCTION_ARGS)
+{
+    int    target_pid = PG_GETARG_INT32(0);
+    int interval = PG_GETARG_INT32(1);
+    PGPROC *target_proc;
+
+    if (interval < 0)
+        ereport(ERROR,
+                (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+                 errmsg("interval must not be a negtive number")));
+
+    LWLockAcquire(ProcArrayLock, LW_SHARED);
+    target_proc = BackendPidGetProcWithLock(target_pid);
+
+    if (target_proc == NULL)
+        ereport(ERROR,
+                (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+                 errmsg("PID %d is not a PostgreSQL server process",
+                        target_pid)));
+
+    /* The same condition to pg_signal_backend() */
+    if ((superuser_arg(target_proc->roleId) && !superuser()) ||
+        (!has_privs_of_role(GetUserId(), target_proc->roleId) &&
+         !has_privs_of_role(GetUserId(), DEFAULT_ROLE_SIGNAL_BACKENDID)))
+        ereport(ERROR,
+                (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+                 errmsg("permission denied")));
+
+    if (target_proc->backendId == InvalidBackendId)
+        ereport(ERROR,
+                (errmsg("invalid backendid")));
+
+    SpinLockAcquire(&CatcacheStatsParamLock);
+    CatcacheStatsParamArray[target_proc->backendId - 1].interval = interval;
+    SpinLockRelease(&CatcacheStatsParamLock);
+    LWLockRelease(ProcArrayLock);
+
+    PG_RETURN_VOID();
+}
+
+/* returns catcache stats paramter of this backend */
+int
+GetCatcacheStatsParam(void)
+{
+    int interval;
+
+    Assert(MyBackendId != InvalidBackendId);
+
+    SpinLockAcquire(&CatcacheStatsParamLock);
+    interval = CatcacheStatsParamArray[MyBackendId - 1].interval;
+    SpinLockRelease(&CatcacheStatsParamLock);
+
+    return interval;
+}    
+
+/* sets catcache stats paramter of this backend */
+void
+SetCatcacheStatsParam(int interval)
+{
+    Assert(MyBackendId != InvalidBackendId);
+    SpinLockAcquire(&CatcacheStatsParamLock);
+    CatcacheStatsParamArray[MyBackendId - 1].interval = interval;
+    SpinLockRelease(&CatcacheStatsParamLock);
+}    
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 11fc1f3075..8011d94d5d 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10518,4 +10518,12 @@
   proargnames => '{rootrelid,relid,parentrelid,isleaf,level}',
   prosrc => 'pg_partition_tree' },
 
+# catcache statitics
+{ oid => '3424',
+  descr => 'take backend statistics of another backend',
+  proname => 'pg_backend_catcache_stats', proisstrict => 'f',
+  proretset => 'f', provolatile => 'v', proparallel => 'u',
+  prorettype => 'void', proargtypes => 'int4 int4',
+  prosrc => 'backend_catcache_stats' },
+
 ]
diff --git a/src/include/utils/catcache.h b/src/include/utils/catcache.h
index 4d51975920..69031f1a5e 100644
--- a/src/include/utils/catcache.h
+++ b/src/include/utils/catcache.h
@@ -24,6 +24,7 @@
 #include "access/skey.h"
 #include "datatype/timestamp.h"
 #include "lib/ilist.h"
+#include "utils/catcache.h"
 #include "utils/relcache.h"
 
 /*
@@ -212,6 +213,9 @@ GetCatCacheClock(void)
     return catcacheclock;
 }
 
+extern Size CatcacheStatsShmemSize(void);
+extern void CatcacheStatsShmemInit(void);
+
 extern void CreateCacheMemoryContext(void);
 
 extern CatCache *InitCatCache(int id, Oid reloid, Oid indexoid,
@@ -254,5 +258,7 @@ extern void PrintCatCacheListLeakWarning(CatCList *list);
 /* defined in syscache.h */
 typedef struct syscachestats SysCacheStats;
 extern void CatCacheGetStats(CatCache *cache, SysCacheStats *syscachestats);
+extern void SetCatcacheStatsParam(int interval);
+extern int GetCatcacheStatsParam(void);
 
 #endif                            /* CATCACHE_H */
-- 
2.16.3


pgsql-hackers by date:

Previous
From: David Rowley
Date:
Subject: Re: pg_dump multi VALUES INSERT
Next
From: Donald Dong
Date:
Subject: Analyze all plans