Re: shared-memory based stats collector

Поиск
Список
Период
Сортировка
От Kyotaro HORIGUCHI
Тема Re: shared-memory based stats collector
Дата
Msg-id 20181005.173017.151015949.horiguchi.kyotaro@lab.ntt.co.jp
обсуждение исходный текст
Ответ на Re: shared-memory based stats collector  (Kyotaro HORIGUCHI <horiguchi.kyotaro@lab.ntt.co.jp>)
Ответы Re: shared-memory based stats collector  (Antonin Houska <ah@cybertec.at>)
Re: shared-memory based stats collector  (Tomas Vondra <tomas.vondra@2ndquadrant.com>)
Re: shared-memory based stats collector  (Tomas Vondra <tomas.vondra@2ndquadrant.com>)
Список pgsql-hackers
Hello.

At Tue, 02 Oct 2018 16:06:51 +0900 (Tokyo Standard Time), Kyotaro HORIGUCHI <horiguchi.kyotaro@lab.ntt.co.jp> wrote in
<20181002.160651.117284090.horiguchi.kyotaro@lab.ntt.co.jp>
> It doesn't work nor even compile since I failed to include some
> changes. The atached v6-0008 at least compiles and words.
> 
> 0001-0007 are not attached since they are still aplicable on
> master head with offsets.

In this patchset 0001-0007 are still the same with the previous
version. I'll reorganize the whole patchset in the next version.

This is more saner version of previous v5-0008, which didn't pass
regression test. v6-0008 to v6-0010 are attached and they are
applied on top of v5-0001-0007.

- stats collector has been removed.

- modified dshash further so that deletion is allowed during
  sequential scan.

- I'm not sure about the following existing comment at the
  beginning of pgstat.c

  *    - Add a pgstat config column to pg_database, so this
  *      entire thing can be enabled/disabled on a per db basis.


Some points known to need some considerations are:

1. Concurrency is controlled by per-database entry in db_stats
   dshash. It has 127 lock partitions but all backends on the
   same database share just one lock and only one backend takes
   the right to update stats. (Every backend doesn't update stats
   with the interval not shorter than 500ms, like the current
   stats collector.)  Table-stats can be removed by DROP DB
   simultaeously with stats updates so need to block it using
   per-databsae lock. Any locking means other than dshash might
   be needed.

2. Since dshash cannot allow multiple locks because of resize,
   pgstat_update_stat is forced to be a bit ineffecient.
   It loops onver stats list twice, for shared tables and regular
   tables since we can acquire lock on one database at once.

   Maybe providing individual TabStatusArray for the two will fix
   it, will do in the next version.

3. This adds a new timeout IDLE_STATS_UPDATE_TIMEOUT. This works
   similarly to IDLE_IN_TRANSACTIION_SESSION_TIMEOUT. It fires in
   at most PGSTAT_STAT_MIN_INTERVAL(500)ms to clean up pending
   statistics update.

regards.

-- 
Kyotaro Horiguchi
NTT Open Source Software Center
From e3d415d4a3d691d2bd7864fdb1ec088d445209e5 Mon Sep 17 00:00:00 2001
From: Kyotaro Horiguchi <horiguchi.kyotaro@lab.ntt.co.jp>
Date: Fri, 5 Oct 2018 16:57:40 +0900
Subject: [PATCH 10/10] Remove stats collector process

Since stats are directly updated by every backend stats collector is
no longer useful. Remove it.
---
 src/backend/bootstrap/bootstrap.c   |   8 --
 src/backend/postmaster/pgstat.c     | 205 ++++--------------------------------
 src/backend/postmaster/postmaster.c |  78 ++------------
 src/backend/storage/ipc/dsm.c       |  15 ++-
 src/include/pgstat.h                |   7 +-
 src/include/storage/dsm.h           |   1 +
 6 files changed, 42 insertions(+), 272 deletions(-)

diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index ece200877c..578af2e66d 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -336,9 +336,6 @@ AuxiliaryProcessMain(int argc, char *argv[])
             case WalReceiverProcess:
                 statmsg = pgstat_get_backend_desc(B_WAL_RECEIVER);
                 break;
-            case StatsCollectorProcess:
-                statmsg = pgstat_get_backend_desc(B_STATS_COLLECTOR);
-                break;
             default:
                 statmsg = "??? process";
                 break;
@@ -473,11 +470,6 @@ AuxiliaryProcessMain(int argc, char *argv[])
             WalReceiverMain();
             proc_exit(1);        /* should never return */
 
-        case StatsCollectorProcess:
-            /* don't set signals, stats collector has its own agenda */
-            PgstatCollectorMain();
-            proc_exit(1);        /* should never return */
-
         default:
             elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
             proc_exit(1);
diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
index cef3097da9..c8818af5b9 100644
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -129,8 +129,6 @@ PgStat_BgWriter BgWriterStats;
  * Local data
  * ----------
  */
-static time_t last_pgstat_start_time;
-
 /* Shared stats bootstrap infomation */
 typedef struct StatsShmemStruct {
     dsa_handle stats_dsa_handle;
@@ -286,11 +284,6 @@ static PgStat_ArchiverStats *snapshot_archiverStats;
 static PgStat_GlobalStats *shared_globalStats;
 static PgStat_GlobalStats *snapshot_globalStats;
 
-/* Signal handler flags */
-static volatile bool need_exit = false;
-static volatile bool got_SIGHUP = false;
-static volatile bool got_SIGTERM = false;
-
 /*
  * Total time charged to functions so far in the current backend.
  * We use this to help separate "self" and "other" time charges.
@@ -303,14 +296,8 @@ static instr_time total_func_time;
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgstat_forkexec(void);
-#endif
-
-static void pgstat_shutdown_handler(SIGNAL_ARGS);
-static void pgstat_quickdie_handler(SIGNAL_ARGS);
+/* functions used in backends */
 static void pgstat_beshutdown_hook(int code, Datum arg);
-static void pgstat_sighup_handler(SIGNAL_ARGS);
 
 static PgStat_StatDBEntry *pgstat_get_db_entry(Oid databaseid, int op,
                                     pg_stat_table_result_status *status);
@@ -357,27 +344,25 @@ static bool pgstat_update_tabentry(dshash_table *tabhash,
 static void pgstat_update_dbentry(PgStat_StatDBEntry *dbentry,
                                   PgStat_TableStatus *stat);
 
-/* file in/out functions */
-static void pgstat_read_statsfiles(void);
-static void pgstat_write_statsfiles(void);
-
 /* ------------------------------------------------------------
  * Public functions called from postmaster follow
  * ------------------------------------------------------------
  */
 
 /* ----------
- * pgstat_init() -
+ * pgstat_child_init() -
  *
- *    Called from postmaster at startup. Create the resources required
- *    by the statistics collector process.  If unable to do so, do not
- *    fail --- better to let the postmaster start with stats collection
- *    disabled.
+ *    Called from InitPostmasterChild at process startup. Initialize static
+ *    variables.
  * ----------
  */
 void
-pgstat_init(void)
+pgstat_child_init(void)
 {
+    StatsShmem->stats_dsa_handle = DSM_HANDLE_INVALID;
+    area = NULL;
+
+    return;
 }
 
 /*
@@ -437,12 +422,6 @@ pgstat_reset_all(void)
     pgstat_reset_remove_files(PGSTAT_STAT_PERMANENT_DIRECTORY);
 }
 
-void
-allow_immediate_pgstat_restart(void)
-{
-    last_pgstat_start_time = 0;
-}
-
 /* ----------
  * pgstat_attach_shared_stats() -
  *
@@ -4384,154 +4363,6 @@ pgstat_update_bgwriter(void)
     MemSet(&BgWriterStats, 0, sizeof(BgWriterStats));
 }
 
-
-/* ----------
- * PgstatCollectorMain() -
- *
- *    Start up the statistics collector process.  This is the body of the
- *    postmaster child process.
- *
- *    The argc/argv parameters are valid only in EXEC_BACKEND case.
- * ----------
- */
-void
-PgstatCollectorMain(void)
-{
-    int            wr;
-
-    /*
-     * Ignore all signals usually bound to some action in the postmaster,
-     * except SIGHUP and SIGQUIT.  Note we don't need a SIGUSR1 handler to
-     * support latch operations, because we only use a local latch.
-     */
-    pqsignal(SIGHUP, pgstat_sighup_handler);
-    pqsignal(SIGINT, SIG_IGN);
-    pqsignal(SIGTERM, pgstat_shutdown_handler);
-    pqsignal(SIGQUIT, pgstat_quickdie_handler);
-    pqsignal(SIGALRM, SIG_IGN);
-    pqsignal(SIGPIPE, SIG_IGN);
-    pqsignal(SIGUSR1, SIG_IGN);
-    pqsignal(SIGUSR2, SIG_IGN);
-    pqsignal(SIGCHLD, SIG_DFL);
-    pqsignal(SIGTTIN, SIG_DFL);
-    pqsignal(SIGTTOU, SIG_DFL);
-    pqsignal(SIGCONT, SIG_DFL);
-    pqsignal(SIGWINCH, SIG_DFL);
-
-    PG_SETMASK(&UnBlockSig);
-
-    /*
-     * Read in existing stats files or initialize the stats to zero.
-     */
-    pgStatRunningInCollector = true;
-    pgstat_read_statsfiles();
-
-    /*
-     * Loop to process messages until we get SIGQUIT or detect ungraceful
-     * death of our parent postmaster.
-     *
-     * For performance reasons, we don't want to do ResetLatch/WaitLatch after
-     * every message; instead, do that only after a recv() fails to obtain a
-     * message.  (This effectively means that if backends are sending us stuff
-     * like mad, we won't notice postmaster death until things slack off a
-     * bit; which seems fine.)    To do that, we have an inner loop that
-     * iterates as long as recv() succeeds.  We do recognize got_SIGHUP inside
-     * the inner loop, which means that such interrupts will get serviced but
-     * the latch won't get cleared until next time there is a break in the
-     * action.
-     */
-    for (;;)
-    {
-        /* Clear any already-pending wakeups */
-        ResetLatch(MyLatch);
-
-        /*
-         * Quit if we get SIGQUIT from the postmaster.
-         */
-        if (got_SIGTERM)
-            break;
-
-        /*
-         * Reload configuration if we got SIGHUP from the postmaster.
-         */
-        if (got_SIGHUP)
-        {
-            got_SIGHUP = false;
-            ProcessConfigFile(PGC_SIGHUP);
-        }
-
-        wr = WaitLatch(MyLatch,
-                       WL_LATCH_SET | WL_POSTMASTER_DEATH,
-                       -1L, WAIT_EVENT_PGSTAT_MAIN);
-
-        /*
-         * Emergency bailout if postmaster has died.  This is to avoid the
-         * necessity for manual cleanup of all postmaster children.
-         */
-        if (wr & WL_POSTMASTER_DEATH)
-            break;
-    }                            /* end of outer loop */
-
-    /*
-     * Save the final stats to reuse at next startup.
-     */
-    pgstat_write_statsfiles();
-
-    exit(0);
-}
-
-
-/* SIGQUIT signal handler for collector process */
-static void
-pgstat_quickdie_handler(SIGNAL_ARGS)
-{
-    PG_SETMASK(&BlockSig);
-
-    /*
-     * We DO NOT want to run proc_exit() callbacks -- we're here because
-     * shared memory may be corrupted, so we don't want to try to clean up our
-     * transaction.  Just nail the windows shut and get out of town.  Now that
-     * there's an atexit callback to prevent third-party code from breaking
-     * things by calling exit() directly, we have to reset the callbacks
-     * explicitly to make this work as intended.
-     */
-    on_exit_reset();
-
-    /*
-     * Note we do exit(2) not exit(0).  This is to force the postmaster into a
-     * system reset cycle if some idiot DBA sends a manual SIGQUIT to a random
-     * backend.  This is necessary precisely because we don't clean up our
-     * shared memory state.  (The "dead man switch" mechanism in pmsignal.c
-     * should ensure the postmaster sees this as a crash, too, but no harm in
-     * being doubly sure.)
-     */
-    exit(2);
-}
-
-/* SIGHUP handler for collector process */
-static void
-pgstat_sighup_handler(SIGNAL_ARGS)
-{
-    int            save_errno = errno;
-
-    got_SIGHUP = true;
-    SetLatch(MyLatch);
-
-    errno = save_errno;
-}
-
-static void
-pgstat_shutdown_handler(SIGNAL_ARGS)
-{
-    int save_errno = errno;
-
-    got_SIGTERM = true;
-
-    SetLatch(MyLatch);
-
-    errno = save_errno;
-}
-
 /*
  * Subroutine to reset stats in a shared database entry
  *
@@ -4700,7 +4531,7 @@ pgstat_get_tab_entry(dshash_table *table, Oid tableoid, bool create)
  *        Write the global statistics file, as well as DB files.
  * ----------
  */
-static void
+void
 pgstat_write_statsfiles(void)
 {
     dshash_seq_status hstat;
@@ -4711,8 +4542,8 @@ pgstat_write_statsfiles(void)
     const char *statfile = PGSTAT_STAT_PERMANENT_FILENAME;
     int            rc;
 
-    /* should be called in stats collector  */
-    Assert(pgStatRunningInCollector);
+    /* should be called from postmaster  */
+    Assert(!IsUnderPostmaster);
 
     elog(DEBUG2, "writing stats file \"%s\"", statfile);
 
@@ -4855,8 +4686,6 @@ pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry)
     char        statfile[MAXPGPATH];
     dshash_table *tbl;
 
-    Assert(pgStatRunningInCollector);
-
     get_dbstat_filename(true, dbid, tmpfile, MAXPGPATH);
     get_dbstat_filename(false, dbid, statfile, MAXPGPATH);
 
@@ -4950,7 +4779,7 @@ pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry)
  *
  * ----------
  */
-static void
+void
 pgstat_read_statsfiles(void)
 {
     PgStat_StatDBEntry *dbentry;
@@ -4962,7 +4791,9 @@ pgstat_read_statsfiles(void)
     dshash_table *tblstats = NULL;
     dshash_table *funcstats = NULL;
 
-    Assert(pgStatRunningInCollector);
+    /* should be called from postmaster  */
+    Assert(!IsUnderPostmaster);
+
     /*
      * The tables will live in pgStatLocalContext.
      */
@@ -5173,7 +5004,9 @@ pgstat_read_db_statsfile(Oid databaseid,
     bool        found;
     char        statfile[MAXPGPATH];
 
-    Assert(pgStatRunningInCollector);
+    /* should be called from postmaster  */
+    Assert(!IsUnderPostmaster);
+
     get_dbstat_filename(false, databaseid, statfile, MAXPGPATH);
 
     /*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 798df0767d..edf6e64e25 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -145,8 +145,7 @@
 #define BACKEND_TYPE_AUTOVAC    0x0002    /* autovacuum worker process */
 #define BACKEND_TYPE_WALSND        0x0004    /* walsender process */
 #define BACKEND_TYPE_BGWORKER    0x0008    /* bgworker process */
-#define BACKEND_TYPE_STATS        0x0010    /* bgworker process */
-#define BACKEND_TYPE_ALL        0x001F    /* OR of all the above */
+#define BACKEND_TYPE_ALL        0x000F    /* OR of all the above */
 
 #define BACKEND_TYPE_WORKER        (BACKEND_TYPE_AUTOVAC | BACKEND_TYPE_BGWORKER)
 
@@ -254,7 +253,6 @@ static pid_t StartupPID = 0,
             WalReceiverPID = 0,
             AutoVacPID = 0,
             PgArchPID = 0,
-            PgStatPID = 0,
             SysLoggerPID = 0;
 
 /* Startup process's status */
@@ -552,7 +550,6 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #define StartCheckpointer()        StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()        StartChildProcess(WalWriterProcess)
 #define StartWalReceiver()        StartChildProcess(WalReceiverProcess)
-#define StartStatsCollector()    StartChildProcess(StatsCollectorProcess)
 
 /* Macros to check exit status of a child process */
 #define EXIT_STATUS_0(st)  ((st) == 0)
@@ -1304,12 +1301,6 @@ PostmasterMain(int argc, char *argv[])
 
     whereToSendOutput = DestNone;
 
-    /*
-     * Initialize stats collection subsystem (this does NOT start the
-     * collector process!)
-     */
-    pgstat_init();
-
     /*
      * Initialize the autovacuum subsystem (again, no process start yet)
      */
@@ -1381,6 +1372,9 @@ PostmasterMain(int argc, char *argv[])
     /* Some workers may be scheduled to start now */
     maybe_start_bgworkers();
 
+    /* Activate stats collector facility */
+    pgstat_read_statsfiles();
+
     status = ServerLoop();
 
     /*
@@ -1762,11 +1756,6 @@ ServerLoop(void)
                 start_autovac_launcher = false; /* signal processed */
         }
 
-        /* If we have lost the stats collector, try to start a new one */
-        if (PgStatPID == 0 &&
-            (pmState == PM_RUN || pmState == PM_HOT_STANDBY))
-            PgStatPID = StartStatsCollector();
-
         /* If we have lost the archiver, try to start a new one. */
         if (PgArchPID == 0 && PgArchStartupAllowed())
             PgArchPID = pgarch_start();
@@ -2565,8 +2554,6 @@ SIGHUP_handler(SIGNAL_ARGS)
             signal_child(PgArchPID, SIGHUP);
         if (SysLoggerPID != 0)
             signal_child(SysLoggerPID, SIGHUP);
-        if (PgStatPID != 0)
-            signal_child(PgStatPID, SIGHUP);
 
         /* Reload authentication config files too */
         if (!load_hba())
@@ -2897,8 +2884,6 @@ reaper(SIGNAL_ARGS)
                 AutoVacPID = StartAutoVacLauncher();
             if (PgArchStartupAllowed() && PgArchPID == 0)
                 PgArchPID = pgarch_start();
-            if (PgStatPID == 0)
-                PgStatPID = StartStatsCollector();
 
             /* workers may be scheduled to start now */
             maybe_start_bgworkers();
@@ -2970,8 +2955,7 @@ reaper(SIGNAL_ARGS)
                  * We can also shut down the stats collector now; there's
                  * nothing left for it to do.
                  */
-                if (PgStatPID != 0)
-                    signal_child(PgStatPID, SIGTERM);
+                pgstat_write_statsfiles();
             }
             else
             {
@@ -3048,22 +3032,6 @@ reaper(SIGNAL_ARGS)
             continue;
         }
 
-        /*
-         * Was it the statistics collector?  If so, just try to start a new
-         * one; no need to force reset of the rest of the system.  (If fail,
-         * we'll try again in future cycles of the main loop.)
-         */
-        if (pid == PgStatPID)
-        {
-            PgStatPID = 0;
-            if (!EXIT_STATUS_0(exitstatus))
-                HandleChildCrash(pid, exitstatus,
-                                 _("statistics collector process"));
-            if (pmState == PM_RUN || pmState == PM_HOT_STANDBY)
-                PgStatPID = StartStatsCollector();
-            continue;
-        }
-
         /* Was it the system logger?  If so, try to start a new one */
         if (pid == SysLoggerPID)
         {
@@ -3510,22 +3478,6 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
         signal_child(PgArchPID, SIGQUIT);
     }
 
-    /*
-     * Force a power-cycle of the pgstat process too.  (This isn't absolutely
-     * necessary, but it seems like a good idea for robustness, and it
-     * simplifies the state-machine logic in the case where a shutdown request
-     * arrives during crash processing.)
-     */
-    if (PgStatPID != 0 && take_action)
-    {
-        ereport(DEBUG2,
-                (errmsg_internal("sending %s to process %d",
-                                 "SIGQUIT",
-                                 (int) PgStatPID)));
-        signal_child(PgStatPID, SIGQUIT);
-        allow_immediate_pgstat_restart();
-    }
-
     /* We do NOT restart the syslogger */
 
     if (Shutdown != ImmediateShutdown)
@@ -3729,8 +3681,6 @@ PostmasterStateMachine(void)
                     SignalChildren(SIGQUIT);
                     if (PgArchPID != 0)
                         signal_child(PgArchPID, SIGQUIT);
-                    if (PgStatPID != 0)
-                        signal_child(PgStatPID, SIGQUIT);
                 }
             }
         }
@@ -3769,8 +3719,7 @@ PostmasterStateMachine(void)
          * normal state transition leading up to PM_WAIT_DEAD_END, or during
          * FatalError processing.
          */
-        if (dlist_is_empty(&BackendList) &&
-            PgArchPID == 0 && PgStatPID == 0)
+        if (dlist_is_empty(&BackendList) && PgArchPID == 0)
         {
             /* These other guys should be dead already */
             Assert(StartupPID == 0);
@@ -3970,8 +3919,6 @@ TerminateChildren(int signal)
         signal_child(AutoVacPID, signal);
     if (PgArchPID != 0)
         signal_child(PgArchPID, signal);
-    if (PgStatPID != 0)
-        signal_child(PgStatPID, signal);
 }
 
 /*
@@ -4969,16 +4916,6 @@ SubPostmasterMain(int argc, char *argv[])
 
         PgArchiverMain(argc, argv); /* does not return */
     }
-    if (strcmp(argv[1], "--forkcol") == 0)
-    {
-        /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
-        InitProcess();
-
-        /* Attach process to shared data structures */
-        CreateSharedMemoryAndSemaphores(false, 0);
-
-        PgstatCollectorMain(argc, argv);    /* does not return */
-    }
     if (strcmp(argv[1], "--forklog") == 0)
     {
         /* Do not want to attach to shared memory */
@@ -5094,8 +5031,7 @@ sigusr1_handler(SIGNAL_ARGS)
         /*
          * Likewise, start other special children as needed.
          */
-        Assert(PgStatPID == 0);
-        PgStatPID = StartStatsCollector();
+        pgstat_read_statsfiles();
 
         ereport(LOG,
                 (errmsg("database system is ready to accept read only connections")));
diff --git a/src/backend/storage/ipc/dsm.c b/src/backend/storage/ipc/dsm.c
index ff0ad4cce3..32508353b7 100644
--- a/src/backend/storage/ipc/dsm.c
+++ b/src/backend/storage/ipc/dsm.c
@@ -432,6 +432,15 @@ dsm_set_control_handle(dsm_handle h)
 }
 #endif
 
+/*
+ * Return if dsm feature is available on this process.
+ */
+bool
+dsm_is_available(void)
+{
+    return dsm_control != NULL;
+}
+
 /*
  * Create a new dynamic shared memory segment.
  *
@@ -449,8 +458,7 @@ dsm_create(Size size, int flags)
     uint32        i;
     uint32        nitems;
 
-    /* Unsafe in postmaster (and pointless in a stand-alone backend). */
-    Assert(IsUnderPostmaster);
+    Assert(dsm_is_available());
 
     if (!dsm_init_done)
         dsm_backend_startup();
@@ -546,8 +554,7 @@ dsm_attach(dsm_handle h)
     uint32        i;
     uint32        nitems;
 
-    /* Unsafe in postmaster (and pointless in a stand-alone backend). */
-    Assert(IsUnderPostmaster);
+    Assert(dsm_is_available());
 
     if (!dsm_init_done)
         dsm_backend_startup();
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 5db631c54c..dad3440568 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -800,10 +800,8 @@ extern PgStat_Counter pgStatBlockWriteTime;
  * Functions called from postmaster
  * ----------
  */
-extern void pgstat_init(void);
-extern int    pgstat_start(void);
+extern void pgstat_child_init(void);
 extern void pgstat_reset_all(void);
-extern void allow_immediate_pgstat_restart(void);
 
 /* ----------
  * Functions called from backends
@@ -1005,4 +1003,7 @@ extern void CreateSharedBackendStatus(void);
 extern Size StatsShmemSize(void);
 extern void StatsShmemInit(void);
 
+extern void pgstat_read_statsfiles(void);
+extern void pgstat_write_statsfiles(void);
+
 #endif                            /* PGSTAT_H */
diff --git a/src/include/storage/dsm.h b/src/include/storage/dsm.h
index 3c3da7ace6..be50f43db0 100644
--- a/src/include/storage/dsm.h
+++ b/src/include/storage/dsm.h
@@ -34,6 +34,7 @@ extern void dsm_detach_all(void);
 extern void dsm_set_control_handle(dsm_handle h);
 #endif
 
+extern bool dsm_is_available(void);
 /* Functions that create, update, or remove mappings. */
 extern dsm_segment *dsm_create(Size size, int flags);
 extern dsm_segment *dsm_attach(dsm_handle h);
-- 
2.16.3

From 68d608a77661d64625247fd04d89d9447b36046a Mon Sep 17 00:00:00 2001
From: Kyotaro Horiguchi <horiguchi.kyotaro@lab.ntt.co.jp>
Date: Thu, 4 Oct 2018 09:26:18 +0900
Subject: [PATCH 09/10] Full shared-memory based stats collector

The version of this patchset at the moment still uses socket as the
channel to collect statistics. However the stats collector process is
the only writer of the shared memory in the way and we don't need to
consider of locking among multiple writers, it is inneficient.

With this patch every backend directly writres to the stats tables. A
updator backend must aquire lock on database stats entry and decline
on lock failure. In regular backends, stats updates don't happen with
the interval shorter than about PGSTAT_STAT_MIN_INTERVAL(500)ms as the
previous stats collector did. On the other hand if pending updates
lasts for longer than PGSTAT_STAT_MAX_INTERVAL(1000)ms, the pending
updates are forcibly applied.
---
 src/backend/access/transam/xlog.c           |    4 +-
 src/backend/postmaster/autovacuum.c         |   16 +-
 src/backend/postmaster/bgwriter.c           |    4 +-
 src/backend/postmaster/checkpointer.c       |   24 +-
 src/backend/postmaster/pgarch.c             |    4 +-
 src/backend/postmaster/pgstat.c             | 2872 +++++++++++----------------
 src/backend/postmaster/postmaster.c         |   10 +
 src/backend/replication/logical/tablesync.c |    9 +-
 src/backend/replication/logical/worker.c    |    4 +-
 src/backend/storage/buffer/bufmgr.c         |    8 +-
 src/backend/storage/ipc/dsm.c               |    9 +
 src/backend/tcop/postgres.c                 |   27 +-
 src/backend/utils/adt/pgstatfuncs.c         |   44 +-
 src/backend/utils/init/globals.c            |    1 +
 src/backend/utils/init/postinit.c           |   11 +
 src/include/miscadmin.h                     |    1 +
 src/include/pgstat.h                        |  381 +---
 src/include/storage/dsm.h                   |    1 +
 src/include/utils/timeout.h                 |    1 +
 src/test/modules/worker_spi/worker_spi.c    |    2 +-
 20 files changed, 1361 insertions(+), 2072 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 7375a78ffc..980c7e9e0e 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -8604,9 +8604,9 @@ LogCheckpointEnd(bool restartpoint)
                         &sync_secs, &sync_usecs);
 
     /* Accumulate checkpoint timing summary data, in milliseconds. */
-    BgWriterStats.m_checkpoint_write_time +=
+    BgWriterStats.checkpoint_write_time +=
         write_secs * 1000 + write_usecs / 1000;
-    BgWriterStats.m_checkpoint_sync_time +=
+    BgWriterStats.checkpoint_sync_time +=
         sync_secs * 1000 + sync_usecs / 1000;
 
     /*
diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 65956c0c35..10e707e9a1 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -977,7 +977,7 @@ rebuild_database_list(Oid newdb)
         PgStat_StatDBEntry *entry;
 
         /* only consider this database if it has a pgstat entry */
-        entry = backend_get_db_entry(newdb, true);
+        entry = pgstat_fetch_stat_dbentry(newdb, true);
         if (entry != NULL)
         {
             /* we assume it isn't found because the hash was just created */
@@ -1002,7 +1002,7 @@ rebuild_database_list(Oid newdb)
          * skip databases with no stat entries -- in particular, this gets rid
          * of dropped databases
          */
-        entry = backend_get_db_entry(avdb->adl_datid, true);
+        entry = pgstat_fetch_stat_dbentry(avdb->adl_datid, true);
         if (entry == NULL)
             continue;
 
@@ -1027,7 +1027,7 @@ rebuild_database_list(Oid newdb)
         PgStat_StatDBEntry *entry;
 
         /* only consider databases with a pgstat entry */
-        entry = backend_get_db_entry(avdb->adw_datid, true);
+        entry = pgstat_fetch_stat_dbentry(avdb->adw_datid, true);
         if (entry == NULL)
             continue;
 
@@ -1238,7 +1238,7 @@ do_start_worker(void)
             continue;            /* ignore not-at-risk DBs */
 
         /* Find pgstat entry if any */
-        tmp->adw_entry = backend_get_db_entry(tmp->adw_datid, true);
+        tmp->adw_entry = pgstat_fetch_stat_dbentry(tmp->adw_datid, true);
 
         /*
          * Skip a database with no pgstat entry; it means it hasn't seen any
@@ -1980,7 +1980,7 @@ do_autovacuum(void)
      * may be NULL if we couldn't find an entry (only happens if we are
      * forcing a vacuum for anti-wrap purposes).
      */
-    dbentry = backend_get_db_entry(MyDatabaseId, true);
+    dbentry = pgstat_fetch_stat_dbentry(MyDatabaseId, true);
 
     /* Start a transaction so our commands have one to play into. */
     StartTransactionCommand();
@@ -2030,7 +2030,7 @@ do_autovacuum(void)
     MemoryContextSwitchTo(AutovacMemCxt);
 
     /* The database hash where pgstat keeps shared relations */
-    shared = backend_get_db_entry(InvalidOid, true);
+    shared = pgstat_fetch_stat_dbentry(InvalidOid, true);
 
     classRel = heap_open(RelationRelationId, AccessShareLock);
 
@@ -2805,8 +2805,8 @@ table_recheck_autovac(Oid relid, HTAB *table_toast_map,
     /* use fresh stats */
     autovac_refresh_stats();
 
-    shared = backend_get_db_entry(InvalidOid, true);
-    dbentry = backend_get_db_entry(MyDatabaseId, true);
+    shared = pgstat_fetch_stat_dbentry(InvalidOid, true);
+    dbentry = pgstat_fetch_stat_dbentry(MyDatabaseId, true);
 
     /* fetch the relation's relcache entry */
     classTup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index b1e9bb2c53..a4b1079e60 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -271,9 +271,9 @@ BackgroundWriterMain(void)
         can_hibernate = BgBufferSync(&wb_context);
 
         /*
-         * Send off activity statistics to the stats collector
+         * Update activity statistics.
          */
-        pgstat_send_bgwriter();
+        pgstat_update_bgwriter();
 
         if (FirstCallSinceLastCheckpoint())
         {
diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c
index 1a033093c5..9235390bc6 100644
--- a/src/backend/postmaster/checkpointer.c
+++ b/src/backend/postmaster/checkpointer.c
@@ -376,7 +376,7 @@ CheckpointerMain(void)
         {
             checkpoint_requested = false;
             do_checkpoint = true;
-            BgWriterStats.m_requested_checkpoints++;
+            BgWriterStats.requested_checkpoints++;
         }
         if (shutdown_requested)
         {
@@ -402,7 +402,7 @@ CheckpointerMain(void)
         if (elapsed_secs >= CheckPointTimeout)
         {
             if (!do_checkpoint)
-                BgWriterStats.m_timed_checkpoints++;
+                BgWriterStats.timed_checkpoints++;
             do_checkpoint = true;
             flags |= CHECKPOINT_CAUSE_TIME;
         }
@@ -520,13 +520,13 @@ CheckpointerMain(void)
         CheckArchiveTimeout();
 
         /*
-         * Send off activity statistics to the stats collector.  (The reason
-         * why we re-use bgwriter-related code for this is that the bgwriter
-         * and checkpointer used to be just one process.  It's probably not
-         * worth the trouble to split the stats support into two independent
-         * stats message types.)
+         * Update activity statistics.  (The reason why we re-use
+         * bgwriter-related code for this is that the bgwriter and
+         * checkpointer used to be just one process.  It's probably not worth
+         * the trouble to split the stats support into two independent
+         * functions.)
          */
-        pgstat_send_bgwriter();
+        pgstat_update_bgwriter();
 
         /*
          * Sleep until we are signaled or it's time for another checkpoint or
@@ -694,9 +694,9 @@ CheckpointWriteDelay(int flags, double progress)
         CheckArchiveTimeout();
 
         /*
-         * Report interim activity statistics to the stats collector.
+         * Register interim activity statistics.
          */
-        pgstat_send_bgwriter();
+        pgstat_update_bgwriter();
 
         /*
          * This sleep used to be connected to bgwriter_delay, typically 200ms.
@@ -1296,8 +1296,8 @@ AbsorbFsyncRequests(void)
     LWLockAcquire(CheckpointerCommLock, LW_EXCLUSIVE);
 
     /* Transfer stats counts into pending pgstats message */
-    BgWriterStats.m_buf_written_backend += CheckpointerShmem->num_backend_writes;
-    BgWriterStats.m_buf_fsync_backend += CheckpointerShmem->num_backend_fsync;
+    BgWriterStats.buf_written_backend += CheckpointerShmem->num_backend_writes;
+    BgWriterStats.buf_fsync_backend += CheckpointerShmem->num_backend_fsync;
 
     CheckpointerShmem->num_backend_writes = 0;
     CheckpointerShmem->num_backend_fsync = 0;
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index 885e85ad8a..3ca36d62a4 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -466,7 +466,7 @@ pgarch_ArchiverCopyLoop(void)
                  * Tell the collector about the WAL file that we successfully
                  * archived
                  */
-                pgstat_send_archiver(xlog, false);
+                pgstat_update_archiver(xlog, false);
 
                 break;            /* out of inner retry loop */
             }
@@ -476,7 +476,7 @@ pgarch_ArchiverCopyLoop(void)
                  * Tell the collector about the WAL file that we failed to
                  * archive
                  */
-                pgstat_send_archiver(xlog, true);
+                pgstat_update_archiver(xlog, true);
 
                 if (++failures >= NUM_ARCHIVE_RETRIES)
                 {
diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
index a3d5f4856f..cef3097da9 100644
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -1,15 +1,10 @@
 /* ----------
  * pgstat.c
  *
- *    All the statistics collector stuff hacked up in one big, ugly file.
+ *    Statistics collector facility.
  *
- *    TODO:    - Separate collector, postmaster and backend stuff
- *              into different files.
- *
- *            - Add some automatic call for pgstat vacuuming.
- *
- *            - Add a pgstat config column to pg_database, so this
- *              entire thing can be enabled/disabled on a per db basis.
+ *    Statistics data is stored in dynamic shared memory. Every backends
+ *    updates and read it individually.
  *
  *    Copyright (c) 2001-2018, PostgreSQL Global Development Group
  *
@@ -74,16 +69,11 @@
  * Timer definitions.
  * ----------
  */
-#define PGSTAT_STAT_INTERVAL    500 /* Minimum time between stats file
-                                     * updates; in milliseconds. */
-
-#define PGSTAT_RESTART_INTERVAL 60    /* How often to attempt to restart a
-                                     * failed statistics collector; in
-                                     * seconds. */
-
-/* Minimum receive buffer size for the collector's socket. */
-#define PGSTAT_MIN_RCVBUF        (100 * 1024)
+#define PGSTAT_STAT_MIN_INTERVAL    500 /* Minimum time between stats data
+                                         * updates; in milliseconds. */
 
+#define PGSTAT_STAT_MAX_INTERVAL   1000 /* Maximum time between stats data
+                                         * updates; in milliseconds. */
 
 /* ----------
  * The initial size hints for the hash tables used in the collector.
@@ -92,6 +82,20 @@
 #define PGSTAT_TAB_HASH_SIZE    512
 #define PGSTAT_FUNCTION_HASH_SIZE    512
 
+/*
+ * Operation mode of pgstat_get_db_entry.
+ */
+#define PGSTAT_TABLE_READ    0
+#define PGSTAT_TABLE_WRITE    1
+#define PGSTAT_TABLE_CREATE 2
+#define    PGSTAT_TABLE_NOWAIT 4
+
+typedef enum
+{
+    PGSTAT_TABLE_NOT_FOUND,
+    PGSTAT_TABLE_FOUND,
+    PGSTAT_TABLE_LOCK_FAILED
+} pg_stat_table_result_status;
 
 /* ----------
  * Total number of backends including auxiliary
@@ -119,20 +123,14 @@ int            pgstat_track_activity_query_size = 1024;
  * Stored directly in a stats message structure so it can be sent
  * without needing to copy things around.  We assume this inits to zeroes.
  */
-PgStat_MsgBgWriter BgWriterStats;
+PgStat_BgWriter BgWriterStats;
 
 /* ----------
  * Local data
  * ----------
  */
-NON_EXEC_STATIC pgsocket pgStatSock = PGINVALID_SOCKET;
-
-static struct sockaddr_storage pgStatAddr;
-
 static time_t last_pgstat_start_time;
 
-static bool pgStatRunningInCollector = false;
-
 /* Shared stats bootstrap infomation */
 typedef struct StatsShmemStruct {
     dsa_handle stats_dsa_handle;
@@ -147,6 +145,16 @@ static dshash_table *db_stats;
 static HTAB *snapshot_db_stats;
 static MemoryContext stats_cxt;
 
+/*
+ *  report withholding facility.
+ *
+ *  some report items are withholded if required lock is not acquired
+ *  immediately.
+ */
+static bool pgstat_pending_recoveryconflict = false;
+static bool pgstat_pending_deadlock = false;
+static bool pgstat_pending_tempfile = false;
+
 /* dshash parameter for each type of table */
 static const dshash_parameters dsh_dbparams = {
     sizeof(Oid),
@@ -205,18 +213,14 @@ typedef struct TabStatHashEntry
  * Hash table for O(1) t_id -> tsa_entry lookup
  */
 static HTAB *pgStatTabHash = NULL;
+static HTAB *pgStatPendingTabHash = NULL;
 
 /*
  * Backends store per-function info that's waiting to be sent to the collector
  * in this hash table (indexed by function OID).
  */
 static HTAB *pgStatFunctions = NULL;
-
-/*
- * Indicates if backend has some function stats that it hasn't yet
- * sent to the collector.
- */
-static bool have_function_stats = false;
+static HTAB *pgStatPendingFunctions = NULL;
 
 /*
  * Tuple insertion/deletion counts for an open transaction can't be propagated
@@ -253,6 +257,12 @@ typedef struct TwoPhasePgStatRecord
     bool        t_truncated;    /* was the relation truncated? */
 } TwoPhasePgStatRecord;
 
+typedef struct
+{
+    dshash_table *tabhash;
+    PgStat_StatDBEntry *dbentry;
+} pgstat_apply_tabstat_context;
+
 /*
  * Info about current "snapshot" of stats file
  */
@@ -276,14 +286,6 @@ static PgStat_ArchiverStats *snapshot_archiverStats;
 static PgStat_GlobalStats *shared_globalStats;
 static PgStat_GlobalStats *snapshot_globalStats;
 
-
-/*
- * List of OIDs of databases we need to write out.  If an entry is InvalidOid,
- * it means to write only the shared-catalog stats ("DB 0"); otherwise, we
- * will write both that DB's data and the shared stats.
- */
-static List *pending_write_requests = NIL;
-
 /* Signal handler flags */
 static volatile bool need_exit = false;
 static volatile bool got_SIGHUP = false;
@@ -305,17 +307,15 @@ static instr_time total_func_time;
 static pid_t pgstat_forkexec(void);
 #endif
 
-/* functions used in stats collector */
 static void pgstat_shutdown_handler(SIGNAL_ARGS);
 static void pgstat_quickdie_handler(SIGNAL_ARGS);
 static void pgstat_beshutdown_hook(int code, Datum arg);
 static void pgstat_sighup_handler(SIGNAL_ARGS);
 
-static PgStat_StatDBEntry *pgstat_get_db_entry(Oid databaseid, bool create);
+static PgStat_StatDBEntry *pgstat_get_db_entry(Oid databaseid, int op,
+                                    pg_stat_table_result_status *status);
 static PgStat_StatTabEntry *pgstat_get_tab_entry(dshash_table *table, Oid tableoid, bool create);
-static void pgstat_write_statsfiles(void);
 static void pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry);
-static void pgstat_read_statsfiles(void);
 static void pgstat_read_db_statsfile(Oid databaseid, dshash_table *tabhash, dshash_table *funchash);
 
 /* functions used in backends */
@@ -323,10 +323,25 @@ static bool backend_snapshot_global_stats(void);
 static PgStat_StatFuncEntry *backend_get_func_etnry(PgStat_StatDBEntry *dbent, Oid funcid, bool oneshot);
 static void pgstat_read_current_status(void);
 
-static void pgstat_send_tabstat(PgStat_MsgTabstat *tsmsg);
-static void pgstat_send_funcstats(void);
-static HTAB *pgstat_collect_oids(Oid catalogid);
+static void pgstat_update_loop(bool shared, bool force,
+                               pgstat_apply_tabstat_context *cxt);
+static bool pgstat_apply_tabstat(pgstat_apply_tabstat_context *cxt,
+                                 PgStat_TableStatus *entry, bool nowait);
+static void pgstat_update_pending_tabhash(PgStat_TableStatus *deststat,
+                                          PgStat_TableStatus *srcstat,
+                                          bool init);
+static void pgstat_update_funcstats(bool force, PgStat_StatDBEntry *dbentry);
+static void pgstat_cleanup_recovery_conflict(PgStat_StatDBEntry *dbentry);
+static void pgstat_cleanup_deadlock(PgStat_StatDBEntry *dbentry);
+static void pgstat_cleanup_tempfile(PgStat_StatDBEntry *dbentry);
 
+static inline void pgstat_update_funcentry_by_backendstats(
+    PgStat_StatFuncEntry *dest, PgStat_BackendFunctionEntry *src, bool init);
+static inline void pgstat_update_funcentry_by_stats(
+    PgStat_StatFuncEntry *dest, PgStat_StatFuncEntry *src, bool init);
+
+static HTAB *pgstat_collect_oids(Oid catalogid);
+static void reset_dbentry_counters(PgStat_StatDBEntry *dbentry);
 static PgStat_TableStatus *get_tabstat_entry(Oid rel_id, bool isshared);
 
 static void pgstat_setup_memcxt(void);
@@ -337,25 +352,14 @@ static const char *pgstat_get_wait_ipc(WaitEventIPC w);
 static const char *pgstat_get_wait_timeout(WaitEventTimeout w);
 static const char *pgstat_get_wait_io(WaitEventIO w);
 
-static void pgstat_setheader(PgStat_MsgHdr *hdr, StatMsgType mtype);
-static void pgstat_send(void *msg, int len);
+static bool pgstat_update_tabentry(dshash_table *tabhash,
+                                   PgStat_TableStatus *stat, bool nowait);
+static void pgstat_update_dbentry(PgStat_StatDBEntry *dbentry,
+                                  PgStat_TableStatus *stat);
 
-static void pgstat_recv_tabstat(PgStat_MsgTabstat *msg, int len);
-static void pgstat_recv_tabpurge(PgStat_MsgTabpurge *msg, int len);
-static void pgstat_recv_dropdb(PgStat_MsgDropdb *msg, int len);
-static void pgstat_recv_resetcounter(PgStat_MsgResetcounter *msg, int len);
-static void pgstat_recv_resetsharedcounter(PgStat_MsgResetsharedcounter *msg, int len);
-static void pgstat_recv_resetsinglecounter(PgStat_MsgResetsinglecounter *msg, int len);
-static void pgstat_recv_autovac(PgStat_MsgAutovacStart *msg, int len);
-static void pgstat_recv_vacuum(PgStat_MsgVacuum *msg, int len);
-static void pgstat_recv_analyze(PgStat_MsgAnalyze *msg, int len);
-static void pgstat_recv_archiver(PgStat_MsgArchiver *msg, int len);
-static void pgstat_recv_bgwriter(PgStat_MsgBgWriter *msg, int len);
-static void pgstat_recv_funcstat(PgStat_MsgFuncstat *msg, int len);
-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);
+/* file in/out functions */
+static void pgstat_read_statsfiles(void);
+static void pgstat_write_statsfiles(void);
 
 /* ------------------------------------------------------------
  * Public functions called from postmaster follow
@@ -374,280 +378,6 @@ static void pgstat_recv_tempfile(PgStat_MsgTempFile *msg, int len);
 void
 pgstat_init(void)
 {
-    ACCEPT_TYPE_ARG3 alen;
-    struct addrinfo *addrs = NULL,
-               *addr,
-                hints;
-    int            ret;
-    fd_set        rset;
-    struct timeval tv;
-    char        test_byte;
-    int            sel_res;
-    int            tries = 0;
-
-#define TESTBYTEVAL ((char) 199)
-
-    /*
-     * This static assertion verifies that we didn't mess up the calculations
-     * involved in selecting maximum payload sizes for our UDP messages.
-     * Because the only consequence of overrunning PGSTAT_MAX_MSG_SIZE would
-     * be silent performance loss from fragmentation, it seems worth having a
-     * compile-time cross-check that we didn't.
-     */
-    StaticAssertStmt(sizeof(PgStat_Msg) <= PGSTAT_MAX_MSG_SIZE,
-                     "maximum stats message size exceeds PGSTAT_MAX_MSG_SIZE");
-
-    /*
-     * Create the UDP socket for sending and receiving statistic messages
-     */
-    hints.ai_flags = AI_PASSIVE;
-    hints.ai_family = AF_UNSPEC;
-    hints.ai_socktype = SOCK_DGRAM;
-    hints.ai_protocol = 0;
-    hints.ai_addrlen = 0;
-    hints.ai_addr = NULL;
-    hints.ai_canonname = NULL;
-    hints.ai_next = NULL;
-    ret = pg_getaddrinfo_all("localhost", NULL, &hints, &addrs);
-    if (ret || !addrs)
-    {
-        ereport(LOG,
-                (errmsg("could not resolve \"localhost\": %s",
-                        gai_strerror(ret))));
-        goto startup_failed;
-    }
-
-    /*
-     * On some platforms, pg_getaddrinfo_all() may return multiple addresses
-     * only one of which will actually work (eg, both IPv6 and IPv4 addresses
-     * when kernel will reject IPv6).  Worse, the failure may occur at the
-     * bind() or perhaps even connect() stage.  So we must loop through the
-     * results till we find a working combination. We will generate LOG
-     * messages, but no error, for bogus combinations.
-     */
-    for (addr = addrs; addr; addr = addr->ai_next)
-    {
-#ifdef HAVE_UNIX_SOCKETS
-        /* Ignore AF_UNIX sockets, if any are returned. */
-        if (addr->ai_family == AF_UNIX)
-            continue;
-#endif
-
-        if (++tries > 1)
-            ereport(LOG,
-                    (errmsg("trying another address for the statistics collector")));
-
-        /*
-         * Create the socket.
-         */
-        if ((pgStatSock = socket(addr->ai_family, SOCK_DGRAM, 0)) == PGINVALID_SOCKET)
-        {
-            ereport(LOG,
-                    (errcode_for_socket_access(),
-                     errmsg("could not create socket for statistics collector: %m")));
-            continue;
-        }
-
-        /*
-         * Bind it to a kernel assigned port on localhost and get the assigned
-         * port via getsockname().
-         */
-        if (bind(pgStatSock, addr->ai_addr, addr->ai_addrlen) < 0)
-        {
-            ereport(LOG,
-                    (errcode_for_socket_access(),
-                     errmsg("could not bind socket for statistics collector: %m")));
-            closesocket(pgStatSock);
-            pgStatSock = PGINVALID_SOCKET;
-            continue;
-        }
-
-        alen = sizeof(pgStatAddr);
-        if (getsockname(pgStatSock, (struct sockaddr *) &pgStatAddr, &alen) < 0)
-        {
-            ereport(LOG,
-                    (errcode_for_socket_access(),
-                     errmsg("could not get address of socket for statistics collector: %m")));
-            closesocket(pgStatSock);
-            pgStatSock = PGINVALID_SOCKET;
-            continue;
-        }
-
-        /*
-         * Connect the socket to its own address.  This saves a few cycles by
-         * not having to respecify the target address on every send. This also
-         * provides a kernel-level check that only packets from this same
-         * address will be received.
-         */
-        if (connect(pgStatSock, (struct sockaddr *) &pgStatAddr, alen) < 0)
-        {
-            ereport(LOG,
-                    (errcode_for_socket_access(),
-                     errmsg("could not connect socket for statistics collector: %m")));
-            closesocket(pgStatSock);
-            pgStatSock = PGINVALID_SOCKET;
-            continue;
-        }
-
-        /*
-         * Try to send and receive a one-byte test message on the socket. This
-         * is to catch situations where the socket can be created but will not
-         * actually pass data (for instance, because kernel packet filtering
-         * rules prevent it).
-         */
-        test_byte = TESTBYTEVAL;
-
-retry1:
-        if (send(pgStatSock, &test_byte, 1, 0) != 1)
-        {
-            if (errno == EINTR)
-                goto retry1;    /* if interrupted, just retry */
-            ereport(LOG,
-                    (errcode_for_socket_access(),
-                     errmsg("could not send test message on socket for statistics collector: %m")));
-            closesocket(pgStatSock);
-            pgStatSock = PGINVALID_SOCKET;
-            continue;
-        }
-
-        /*
-         * There could possibly be a little delay before the message can be
-         * received.  We arbitrarily allow up to half a second before deciding
-         * it's broken.
-         */
-        for (;;)                /* need a loop to handle EINTR */
-        {
-            FD_ZERO(&rset);
-            FD_SET(pgStatSock, &rset);
-
-            tv.tv_sec = 0;
-            tv.tv_usec = 500000;
-            sel_res = select(pgStatSock + 1, &rset, NULL, NULL, &tv);
-            if (sel_res >= 0 || errno != EINTR)
-                break;
-        }
-        if (sel_res < 0)
-        {
-            ereport(LOG,
-                    (errcode_for_socket_access(),
-                     errmsg("select() failed in statistics collector: %m")));
-            closesocket(pgStatSock);
-            pgStatSock = PGINVALID_SOCKET;
-            continue;
-        }
-        if (sel_res == 0 || !FD_ISSET(pgStatSock, &rset))
-        {
-            /*
-             * This is the case we actually think is likely, so take pains to
-             * give a specific message for it.
-             *
-             * errno will not be set meaningfully here, so don't use it.
-             */
-            ereport(LOG,
-                    (errcode(ERRCODE_CONNECTION_FAILURE),
-                     errmsg("test message did not get through on socket for statistics collector")));
-            closesocket(pgStatSock);
-            pgStatSock = PGINVALID_SOCKET;
-            continue;
-        }
-
-        test_byte++;            /* just make sure variable is changed */
-
-retry2:
-        if (recv(pgStatSock, &test_byte, 1, 0) != 1)
-        {
-            if (errno == EINTR)
-                goto retry2;    /* if interrupted, just retry */
-            ereport(LOG,
-                    (errcode_for_socket_access(),
-                     errmsg("could not receive test message on socket for statistics collector: %m")));
-            closesocket(pgStatSock);
-            pgStatSock = PGINVALID_SOCKET;
-            continue;
-        }
-
-        if (test_byte != TESTBYTEVAL)    /* strictly paranoia ... */
-        {
-            ereport(LOG,
-                    (errcode(ERRCODE_INTERNAL_ERROR),
-                     errmsg("incorrect test message transmission on socket for statistics collector")));
-            closesocket(pgStatSock);
-            pgStatSock = PGINVALID_SOCKET;
-            continue;
-        }
-
-        /* If we get here, we have a working socket */
-        break;
-    }
-
-    /* Did we find a working address? */
-    if (!addr || pgStatSock == PGINVALID_SOCKET)
-        goto startup_failed;
-
-    /*
-     * Set the socket to non-blocking IO.  This ensures that if the collector
-     * falls behind, statistics messages will be discarded; backends won't
-     * block waiting to send messages to the collector.
-     */
-    if (!pg_set_noblock(pgStatSock))
-    {
-        ereport(LOG,
-                (errcode_for_socket_access(),
-                 errmsg("could not set statistics collector socket to nonblocking mode: %m")));
-        goto startup_failed;
-    }
-
-    /*
-     * Try to ensure that the socket's receive buffer is at least
-     * PGSTAT_MIN_RCVBUF bytes, so that it won't easily overflow and lose
-     * data.  Use of UDP protocol means that we are willing to lose data under
-     * heavy load, but we don't want it to happen just because of ridiculously
-     * small default buffer sizes (such as 8KB on older Windows versions).
-     */
-    {
-        int            old_rcvbuf;
-        int            new_rcvbuf;
-        ACCEPT_TYPE_ARG3 rcvbufsize = sizeof(old_rcvbuf);
-
-        if (getsockopt(pgStatSock, SOL_SOCKET, SO_RCVBUF,
-                       (char *) &old_rcvbuf, &rcvbufsize) < 0)
-        {
-            elog(LOG, "getsockopt(SO_RCVBUF) failed: %m");
-            /* if we can't get existing size, always try to set it */
-            old_rcvbuf = 0;
-        }
-
-        new_rcvbuf = PGSTAT_MIN_RCVBUF;
-        if (old_rcvbuf < new_rcvbuf)
-        {
-            if (setsockopt(pgStatSock, SOL_SOCKET, SO_RCVBUF,
-                           (char *) &new_rcvbuf, sizeof(new_rcvbuf)) < 0)
-                elog(LOG, "setsockopt(SO_RCVBUF) failed: %m");
-        }
-    }
-
-    pg_freeaddrinfo_all(hints.ai_family, addrs);
-
-    return;
-
-startup_failed:
-    ereport(LOG,
-            (errmsg("disabling statistics collector for lack of working socket")));
-
-    if (addrs)
-        pg_freeaddrinfo_all(hints.ai_family, addrs);
-
-    if (pgStatSock != PGINVALID_SOCKET)
-        closesocket(pgStatSock);
-    pgStatSock = PGINVALID_SOCKET;
-
-    /*
-     * Adjust GUC variables to suppress useless activity, and for debugging
-     * purposes (seeing track_counts off is a clue that we failed here). We
-     * use PGC_S_OVERRIDE because there is no point in trying to turn it back
-     * on from postgresql.conf without a restart.
-     */
-    SetConfigOption("track_counts", "off", PGC_INTERNAL, PGC_S_OVERRIDE);
 }
 
 /*
@@ -713,226 +443,6 @@ allow_immediate_pgstat_restart(void)
     last_pgstat_start_time = 0;
 }
 
-/* ------------------------------------------------------------
- * Public functions used by backends follow
- *------------------------------------------------------------
- */
-
-
-/* ----------
- * pgstat_report_stat() -
- *
- *    Must be called by processes that performs DML: tcop/postgres.c, logical
- *    receiver processes, SPI worker, etc. to send the so far collected
- *    per-table and function usage statistics to the collector.  Note that this
- *    is called only when not within a transaction, so it is fair to use
- *    transaction stop time as an approximation of current time.
- * ----------
- */
-void
-pgstat_report_stat(bool force)
-{
-    /* we assume this inits to all zeroes: */
-    static const PgStat_TableCounts all_zeroes;
-    static TimestampTz last_report = 0;
-
-    TimestampTz now;
-    PgStat_MsgTabstat regular_msg;
-    PgStat_MsgTabstat shared_msg;
-    TabStatusArray *tsa;
-    int            i;
-
-    /* Don't expend a clock check if nothing to do */
-    if ((pgStatTabList == NULL || pgStatTabList->tsa_used == 0) &&
-        pgStatXactCommit == 0 && pgStatXactRollback == 0 &&
-        !have_function_stats)
-        return;
-
-    /*
-     * Don't send a message unless it's been at least PGSTAT_STAT_INTERVAL
-     * msec since we last sent one, or the caller wants to force stats out.
-     */
-    now = GetCurrentTransactionStopTimestamp();
-    if (!force &&
-        !TimestampDifferenceExceeds(last_report, now, PGSTAT_STAT_INTERVAL))
-        return;
-    last_report = now;
-
-    /*
-     * Destroy pgStatTabHash before we start invalidating PgStat_TableEntry
-     * entries it points to.  (Should we fail partway through the loop below,
-     * it's okay to have removed the hashtable already --- the only
-     * consequence is we'd get multiple entries for the same table in the
-     * pgStatTabList, and that's safe.)
-     */
-    if (pgStatTabHash)
-        hash_destroy(pgStatTabHash);
-    pgStatTabHash = NULL;
-
-    /*
-     * Scan through the TabStatusArray struct(s) to find tables that actually
-     * have counts, and build messages to send.  We have to separate shared
-     * relations from regular ones because the databaseid field in the message
-     * header has to depend on that.
-     */
-    regular_msg.m_databaseid = MyDatabaseId;
-    shared_msg.m_databaseid = InvalidOid;
-    regular_msg.m_nentries = 0;
-    shared_msg.m_nentries = 0;
-
-    for (tsa = pgStatTabList; tsa != NULL; tsa = tsa->tsa_next)
-    {
-        for (i = 0; i < tsa->tsa_used; i++)
-        {
-            PgStat_TableStatus *entry = &tsa->tsa_entries[i];
-            PgStat_MsgTabstat *this_msg;
-            PgStat_TableEntry *this_ent;
-
-            /* Shouldn't have any pending transaction-dependent counts */
-            Assert(entry->trans == NULL);
-
-            /*
-             * Ignore entries that didn't accumulate any actual counts, such
-             * as indexes that were opened by the planner but not used.
-             */
-            if (memcmp(&entry->t_counts, &all_zeroes,
-                       sizeof(PgStat_TableCounts)) == 0)
-                continue;
-
-            /*
-             * OK, insert data into the appropriate message, and send if full.
-             */
-            this_msg = entry->t_shared ? &shared_msg : ®ular_msg;
-            this_ent = &this_msg->m_entry[this_msg->m_nentries];
-            this_ent->t_id = entry->t_id;
-            memcpy(&this_ent->t_counts, &entry->t_counts,
-                   sizeof(PgStat_TableCounts));
-            if (++this_msg->m_nentries >= PGSTAT_NUM_TABENTRIES)
-            {
-                pgstat_send_tabstat(this_msg);
-                this_msg->m_nentries = 0;
-            }
-        }
-        /* zero out TableStatus structs after use */
-        MemSet(tsa->tsa_entries, 0,
-               tsa->tsa_used * sizeof(PgStat_TableStatus));
-        tsa->tsa_used = 0;
-    }
-
-    /*
-     * Send partial messages.  Make sure that any pending xact commit/abort
-     * gets counted, even if there are no table stats to send.
-     */
-    if (regular_msg.m_nentries > 0 ||
-        pgStatXactCommit > 0 || pgStatXactRollback > 0)
-        pgstat_send_tabstat(®ular_msg);
-    if (shared_msg.m_nentries > 0)
-        pgstat_send_tabstat(&shared_msg);
-
-    /* Now, send function statistics */
-    pgstat_send_funcstats();
-}
-
-/*
- * Subroutine for pgstat_report_stat: finish and send a tabstat message
- */
-static void
-pgstat_send_tabstat(PgStat_MsgTabstat *tsmsg)
-{
-    int            n;
-    int            len;
-
-    /* It's unlikely we'd get here with no socket, but maybe not impossible */
-    if (pgStatSock == PGINVALID_SOCKET)
-        return;
-
-    /*
-     * Report and reset accumulated xact commit/rollback and I/O timings
-     * whenever we send a normal tabstat message
-     */
-    if (OidIsValid(tsmsg->m_databaseid))
-    {
-        tsmsg->m_xact_commit = pgStatXactCommit;
-        tsmsg->m_xact_rollback = pgStatXactRollback;
-        tsmsg->m_block_read_time = pgStatBlockReadTime;
-        tsmsg->m_block_write_time = pgStatBlockWriteTime;
-        pgStatXactCommit = 0;
-        pgStatXactRollback = 0;
-        pgStatBlockReadTime = 0;
-        pgStatBlockWriteTime = 0;
-    }
-    else
-    {
-        tsmsg->m_xact_commit = 0;
-        tsmsg->m_xact_rollback = 0;
-        tsmsg->m_block_read_time = 0;
-        tsmsg->m_block_write_time = 0;
-    }
-
-    n = tsmsg->m_nentries;
-    len = offsetof(PgStat_MsgTabstat, m_entry[0]) +
-        n * sizeof(PgStat_TableEntry);
-
-    pgstat_setheader(&tsmsg->m_hdr, PGSTAT_MTYPE_TABSTAT);
-    pgstat_send(tsmsg, len);
-}
-
-/*
- * Subroutine for pgstat_report_stat: populate and send a function stat message
- */
-static void
-pgstat_send_funcstats(void)
-{
-    /* we assume this inits to all zeroes: */
-    static const PgStat_FunctionCounts all_zeroes;
-
-    PgStat_MsgFuncstat msg;
-    PgStat_BackendFunctionEntry *entry;
-    HASH_SEQ_STATUS fstat;
-
-    if (pgStatFunctions == NULL)
-        return;
-
-    pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_FUNCSTAT);
-    msg.m_databaseid = MyDatabaseId;
-    msg.m_nentries = 0;
-
-    hash_seq_init(&fstat, pgStatFunctions);
-    while ((entry = (PgStat_BackendFunctionEntry *) hash_seq_search(&fstat)) != NULL)
-    {
-        PgStat_FunctionEntry *m_ent;
-
-        /* Skip it if no counts accumulated since last time */
-        if (memcmp(&entry->f_counts, &all_zeroes,
-                   sizeof(PgStat_FunctionCounts)) == 0)
-            continue;
-
-        /* need to convert format of time accumulators */
-        m_ent = &msg.m_entry[msg.m_nentries];
-        m_ent->f_id = entry->f_id;
-        m_ent->f_numcalls = entry->f_counts.f_numcalls;
-        m_ent->f_total_time = INSTR_TIME_GET_MICROSEC(entry->f_counts.f_total_time);
-        m_ent->f_self_time = INSTR_TIME_GET_MICROSEC(entry->f_counts.f_self_time);
-
-        if (++msg.m_nentries >= PGSTAT_NUM_FUNCENTRIES)
-        {
-            pgstat_send(&msg, offsetof(PgStat_MsgFuncstat, m_entry[0]) +
-                        msg.m_nentries * sizeof(PgStat_FunctionEntry));
-            msg.m_nentries = 0;
-        }
-
-        /* reset the entry's counts */
-        MemSet(&entry->f_counts, 0, sizeof(PgStat_FunctionCounts));
-    }
-
-    if (msg.m_nentries > 0)
-        pgstat_send(&msg, offsetof(PgStat_MsgFuncstat, m_entry[0]) +
-                    msg.m_nentries * sizeof(PgStat_FunctionEntry));
-
-    have_function_stats = false;
-}
-
-
 /* ----------
  * pgstat_attach_shared_stats() -
  *
@@ -1008,6 +518,564 @@ pgstat_create_shared_stats(void)
     LWLockRelease(StatsLock);
 }
 
+
+/* ------------------------------------------------------------
+ * Public functions used by backends follow
+ *------------------------------------------------------------
+ */
+
+
+/* ----------
+ * pgstat_report_stat() -
+ *
+ *    Must be called by processes that performs DML: tcop/postgres.c, logical
+ *    receiver processes, SPI worker, etc. to apply the so far collected
+ *    per-table and function usage statistics to the shared statistics hashes.
+ *
+ *  This requires taking some locks on the shared statistics hashes and some
+ *  of updates may be withholded on lock failure. Pending updates are
+ *  retried in later call of this function and finally cleaned up by calling
+ *  this function with force = true or PGSTAT_STAT_MAX_INTERVAL milliseconds
+ *  was elapsed since last cleanup. On the other hand updates by regular
+ *  backends happen with the interval not shorter than
+ *  PGSTAT_STAT_MIN_INTERVAL when force = false.
+ *
+ *  Returns time in milliseconds until the next update time.
+ *
+ *    Note that this is called only when not within a transaction, so it is fair
+ *    to use transaction stop time as an approximation of current time.
+ *    ----------
+ */
+long
+pgstat_update_stat(bool force)
+{
+    /* we assume this inits to all zeroes: */
+    static TimestampTz last_report = 0;
+    static TimestampTz oldest_pending = 0;
+    TimestampTz now;
+    TabStatusArray *tsa;
+    pgstat_apply_tabstat_context cxt;
+    bool        other_pending_stats = false;
+    long elapsed;
+    long secs;
+    int     usecs;
+
+    if (pgstat_pending_recoveryconflict ||
+        pgstat_pending_deadlock ||
+        pgstat_pending_tempfile ||
+        pgStatPendingFunctions)
+        other_pending_stats = true;
+
+    /* Don't expend a clock check if nothing to do */
+    if (!other_pending_stats && !pgStatPendingTabHash &&
+        (pgStatTabList == NULL || pgStatTabList->tsa_used == 0) &&
+        pgStatXactCommit == 0 && pgStatXactRollback == 0)
+        return 0;
+
+    if (!force)
+    {
+        /*
+         * Don't update shared stats unless it's been at least
+         * PGSTAT_STAT_MIN_INTERVAL msec since we last updated one.
+         * Returns time to wait in the case.
+         */
+        now = GetCurrentTransactionStopTimestamp();
+        TimestampDifference(last_report, now, &secs, &usecs);
+        elapsed = secs * 1000 + usecs /1000;
+        
+        if(elapsed < PGSTAT_STAT_MIN_INTERVAL)
+        {
+            /* we know we have some statistics */
+            if (oldest_pending == 0)
+                oldest_pending = now;
+
+            return PGSTAT_STAT_MIN_INTERVAL - elapsed;
+        }
+
+
+        /*
+         * Don't keep pending stats for longer than PGSTAT_STAT_MAX_INTERVAL.
+         */
+        if (oldest_pending > 0)
+        {
+            TimestampDifference(oldest_pending, now, &secs, &usecs);
+            elapsed = secs * 1000 + usecs /1000;
+
+            if(elapsed > PGSTAT_STAT_MAX_INTERVAL)
+                force = true;
+        }
+    }
+
+    last_report = now;
+
+    /* setup stats update context*/
+    cxt.dbentry = NULL;
+    cxt.tabhash = NULL;
+
+    /* Forecibly update other stats if any. */
+    if (other_pending_stats)
+    {
+        cxt.dbentry =
+            pgstat_get_db_entry(MyDatabaseId,
+                                PGSTAT_TABLE_WRITE | PGSTAT_TABLE_CREATE,
+                                NULL);
+
+        /* clean up pending statistics if any */
+        if (pgStatPendingFunctions)
+            pgstat_update_funcstats(true, cxt.dbentry);
+        if (pgstat_pending_recoveryconflict)
+            pgstat_cleanup_recovery_conflict(cxt.dbentry);
+        if (pgstat_pending_deadlock)
+            pgstat_cleanup_deadlock(cxt.dbentry);
+        if (pgstat_pending_tempfile)
+            pgstat_cleanup_tempfile(cxt.dbentry);
+    }
+
+    /*
+     * Destroy pgStatTabHash before we start invalidating PgStat_TableEntry
+     * entries it points to.  (Should we fail partway through the loop below,
+     * it's okay to have removed the hashtable already --- the only
+     * consequence is we'd get multiple entries for the same table in the
+     * pgStatTabList, and that's safe.)
+     */
+    if (pgStatTabHash)
+        hash_destroy(pgStatTabHash);
+    pgStatTabHash = NULL;
+
+    /*
+     * XX: We cannot lock two dshash entries at once. Since we must keep lock
+     * while tables stats are being updated we have no choice other than
+     * separating jobs for shared table stats and that of egular tables.
+     * Looping over the array twice isapparently ineffcient and more efficient
+     * way is expected.
+     */
+
+    /* The first call of the followings uses dbentry obtained above if any.*/
+    pgstat_update_loop(false, force, &cxt);
+    pgstat_update_loop(true, force, &cxt);
+
+    /* zero out TableStatus structs after use */
+    for (tsa = pgStatTabList; tsa != NULL; tsa = tsa->tsa_next)
+    {
+        MemSet(tsa->tsa_entries, 0,
+               tsa->tsa_used * sizeof(PgStat_TableStatus));
+        tsa->tsa_used = 0;
+    }
+
+    /* record oldest pending update time */
+    if (pgStatPendingTabHash == NULL)
+        oldest_pending = 0;
+    else if (oldest_pending == 0)
+        oldest_pending = now;
+
+    return 0;
+}
+
+static void
+pgstat_update_loop(bool shared, bool force, pgstat_apply_tabstat_context *cxt)
+{
+    static const PgStat_TableCounts all_zeroes;
+    TabStatusArray *tsa;
+    int i;
+
+    for (tsa = pgStatTabList; tsa != NULL; tsa = tsa->tsa_next)
+    {
+        for (i = 0; i < tsa->tsa_used; i++)
+        {
+            PgStat_TableStatus *entry = &tsa->tsa_entries[i];
+            PgStat_TableStatus *pentry = NULL;
+
+            /* Shouldn't have any pending transaction-dependent counts */
+            Assert(entry->trans == NULL);
+
+            /*
+             * Ignore entries that didn't accumulate any actual counts, such
+             * as indexes that were opened by the planner but not used.
+             */
+            if (memcmp(&entry->t_counts, &all_zeroes,
+                       sizeof(PgStat_TableCounts)) == 0)
+                continue;
+
+            /* Skip if this entry is not match the request */
+            if (entry->t_shared != shared)
+                continue;
+
+            /* if pending update exists, it should be applied along with */
+            if (pgStatPendingTabHash != NULL)
+            {
+                pentry = hash_search(pgStatPendingTabHash,
+                                     (void *) entry, HASH_FIND, NULL);
+
+                if (pentry)
+                {
+                    /* merge new update into pending updates */
+                    pgstat_update_pending_tabhash(pentry, entry, false);
+                    entry = pentry;
+                }
+            }
+
+            /* try it */
+            if (pgstat_apply_tabstat(cxt, entry, !force))
+            {
+                /* succeeded. remove it if it was pending stats */
+                if (pentry && entry != pentry)
+                    hash_search(pgStatPendingTabHash,
+                                (void *) pentry, HASH_REMOVE, NULL);
+            }
+            else if (!pentry)
+            {
+                /* failed and there was no pending entry, create new one. */
+                bool found;
+
+                if (pgStatPendingTabHash == NULL)
+                {
+                    HASHCTL        ctl;
+
+                    memset(&ctl, 0, sizeof(ctl));
+                    ctl.keysize = sizeof(Oid);
+                    ctl.entrysize = sizeof(PgStat_TableStatus);
+                    pgStatPendingTabHash =
+                        hash_create("pgstat pending table stats hash",
+                                    TABSTAT_QUANTUM,
+                                    &ctl,
+                                    HASH_ELEM | HASH_BLOBS);
+                }
+
+                pentry = hash_search(pgStatPendingTabHash,
+                                     (void *) entry, HASH_ENTER, &found);
+                Assert (!found);
+
+                *pentry = *entry;
+            }
+        }
+    }
+
+    /* if any pending stats exists, try to clean it up */
+    if (pgStatPendingTabHash != NULL)
+    {
+        HASH_SEQ_STATUS pstat;
+        PgStat_TableStatus *pentry;
+
+        hash_seq_init(&pstat, pgStatPendingTabHash);
+        while((pentry = (PgStat_TableStatus *) hash_seq_search(&pstat)) != NULL)
+        {
+            /* Skip if this entry is not match the request */
+            if (pentry->t_shared != shared)
+                continue;
+
+            /* apply pending entry and remove on success */
+            if (pgstat_apply_tabstat(cxt, pentry, !force))
+                hash_search(pgStatPendingTabHash,
+                            (void *) pentry, HASH_REMOVE, NULL);
+        }
+
+        /* destroy the hash if no entry is left */
+        if (hash_get_num_entries(pgStatPendingTabHash) == 0)
+        {
+            hash_destroy(pgStatPendingTabHash);
+            pgStatPendingTabHash = NULL;
+        }
+    }
+
+    if (cxt->tabhash)
+        dshash_detach(cxt->tabhash);
+    if (cxt->dbentry)
+        dshash_release_lock(db_stats, cxt->dbentry);
+    cxt->tabhash = NULL;
+    cxt->dbentry = NULL;
+}
+
+
+/*
+ * pgstat_apply_tabstat: update shared statistics using given entry
+ *
+ * If nowait is true, skips work and returns false on lock failure.
+ * Table stats dshash and function stats dshash are kept attached and stored
+ * in ctx. The caller must detach them after use.
+ */
+bool
+pgstat_apply_tabstat(pgstat_apply_tabstat_context *cxt,
+                     PgStat_TableStatus *entry, bool nowait)
+{
+    Oid dboid = entry->t_shared ? InvalidOid : MyDatabaseId;
+    int        table_mode = PGSTAT_TABLE_WRITE | PGSTAT_TABLE_CREATE;
+    bool updated = false;
+
+    /* fix table search mode */
+    if (nowait)
+        table_mode |= PGSTAT_TABLE_NOWAIT;
+
+    /*
+     * We need to keep lock on dbentries for regular tables to avoid race
+     * condition with drop database. So we hold it in the context variable. We
+     * don't need that for dbentries for shared tables.
+     */
+    if (!cxt->dbentry)
+        cxt->dbentry = pgstat_get_db_entry(dboid, table_mode, NULL);
+
+    /* we cannot acquire lock, just return */
+    if (!cxt->dbentry)
+        return false;
+
+    /* attach shared stats table if not yet */
+    if (!cxt->tabhash)
+    {
+        /* apply database stats  */
+        if (!entry->t_shared)
+        {
+            /* Update database-wide stats  */
+            cxt->dbentry->n_xact_commit += pgStatXactCommit;
+            cxt->dbentry->n_xact_rollback += pgStatXactRollback;
+            cxt->dbentry->n_block_read_time += pgStatBlockReadTime;
+            cxt->dbentry->n_block_write_time += pgStatBlockWriteTime;
+            pgStatXactCommit = 0;
+            pgStatXactRollback = 0;
+            pgStatBlockReadTime = 0;
+            pgStatBlockWriteTime = 0;
+        }
+        
+        cxt->tabhash =
+            dshash_attach(area, &dsh_tblparams, cxt->dbentry->tables, 0);
+    }
+
+    /*
+     * If we have access to the required data, try update table stats first.
+     * Update database stats only if the first step suceeded.
+     */
+    if (pgstat_update_tabentry(cxt->tabhash, entry, nowait))
+    {
+        pgstat_update_dbentry(cxt->dbentry, entry);
+        updated = true;
+    }
+
+    return updated;
+}
+
+/*
+ * pgstat_update_pending_tabhash:
+ *
+ * Updates deststat by adding srcstat. Existing value in deststat is cleard if
+ * init is true.
+ */
+static void
+pgstat_update_pending_tabhash(PgStat_TableStatus *deststat,
+                              PgStat_TableStatus *srcstat,
+                              bool init)
+{
+    Assert (deststat != srcstat);
+
+    if (init)
+        deststat->t_counts = srcstat->t_counts;
+    else
+    {
+        PgStat_TableCounts *dest = &deststat->t_counts;
+        PgStat_TableCounts *src = &srcstat->t_counts;
+
+        dest->t_numscans += src->t_numscans;
+        dest->t_tuples_returned += src->t_tuples_returned;
+        dest->t_tuples_fetched += src->t_tuples_fetched;
+        dest->t_tuples_inserted += src->t_tuples_inserted;
+        dest->t_tuples_updated += src->t_tuples_updated;
+        dest->t_tuples_deleted += src->t_tuples_deleted;
+        dest->t_tuples_hot_updated += src->t_tuples_hot_updated;
+        dest->t_truncated |= src->t_truncated;
+
+        /* If table was truncated, first reset the live/dead counters */
+        if (src->t_truncated)
+        {
+            dest->t_delta_live_tuples = 0;
+            dest->t_delta_dead_tuples = 0;
+        }
+        dest->t_delta_live_tuples += src->t_delta_live_tuples;
+        dest->t_delta_dead_tuples += src->t_delta_dead_tuples;
+        dest->t_changed_tuples += src->t_changed_tuples;
+        dest->t_blocks_fetched += src->t_blocks_fetched;
+        dest->t_blocks_hit += src->t_blocks_hit;
+    }
+}
+        
+/*
+ * Subroutine for pgstat_update_stat: update a function stat
+ */
+static void
+pgstat_update_funcstats(bool force, PgStat_StatDBEntry *dbentry)
+{
+    /* we assume this inits to all zeroes: */
+    static const PgStat_FunctionCounts all_zeroes;
+    pg_stat_table_result_status status = 0;
+    dshash_table *funchash;
+    bool          nowait = !force;
+    bool          release_db = false;
+    int              table_op = PGSTAT_TABLE_WRITE | PGSTAT_TABLE_CREATE;
+
+    if (pgStatFunctions == NULL && pgStatPendingFunctions == NULL)
+        return;
+
+    if (nowait)
+        table_op += PGSTAT_TABLE_NOWAIT;
+
+    /* find the shared function stats table */
+    if (!dbentry)
+    {
+        dbentry = pgstat_get_db_entry(MyDatabaseId, table_op, &status);
+        release_db = true;
+    }
+
+    /* lock failure, return. */
+    if (status == PGSTAT_TABLE_LOCK_FAILED)
+        return;
+
+    funchash = dshash_attach(area, &dsh_funcparams, dbentry->functions, 0);
+
+    /*
+     * First, we empty the transaction stats. Just move numbers to pending
+     * stats if any. Elsewise try to directly update the shared stats but
+     * create a new pending entry on lock failure.
+     */
+    if (pgStatFunctions)
+    {
+        HASH_SEQ_STATUS fstat;
+        PgStat_BackendFunctionEntry *srcent;
+
+        hash_seq_init(&fstat, pgStatFunctions);
+        while ((srcent = (PgStat_BackendFunctionEntry *) hash_seq_search(&fstat)) != NULL)
+        {
+            bool found;
+            bool init = false;
+            PgStat_StatFuncEntry *destent = NULL;
+
+            /* Skip it if no counts accumulated since last time */
+            if (memcmp(&srcent->f_counts, &all_zeroes,
+                       sizeof(PgStat_FunctionCounts)) == 0)
+                continue;
+
+            /* find pending entry */
+            if (pgStatPendingFunctions)
+                destent = (PgStat_StatFuncEntry *)
+                    hash_search(pgStatPendingFunctions,
+                                (void *) &(srcent->f_id), HASH_FIND, NULL);
+
+            if (!destent)
+            {
+                /* pending entry not found, find shared stats entry */
+                destent = (PgStat_StatFuncEntry *)
+                    dshash_find_or_insert_extended(funchash,
+                                                   (void *) &(srcent->f_id),
+                                                   &found, nowait);
+                if (destent)
+                    init = !found;
+                else
+                {
+                    /* no shared stats entry. create a new pending one */
+                    destent = (PgStat_StatFuncEntry *)
+                        hash_search(pgStatPendingFunctions,
+                                    (void *) &(srcent->f_id), HASH_ENTER, NULL);
+                    init = true;
+                }
+            }
+            Assert (destent != NULL);
+
+            pgstat_update_funcentry_by_backendstats(destent, srcent, init);
+
+            /* reset used counts */
+            MemSet(&srcent->f_counts, 0, sizeof(PgStat_FunctionCounts));
+        }
+    }
+
+    /* Second, apply pending stats numbers to shared table */
+    if (pgStatPendingFunctions)
+    {
+        HASH_SEQ_STATUS fstat;
+        PgStat_StatFuncEntry *srcent;
+
+        hash_seq_init(&fstat, pgStatPendingFunctions);
+        while ((srcent = (PgStat_StatFuncEntry *) hash_seq_search(&fstat)) != NULL)
+        {
+            PgStat_StatFuncEntry *destent;
+            bool found;
+
+            destent = (PgStat_StatFuncEntry *)
+                dshash_find_or_insert_extended(funchash,
+                                               (void *) &(srcent->functionid),
+                                               &found, nowait);
+            if (destent)
+            {
+                pgstat_update_funcentry_by_stats(srcent, destent, !found);
+                hash_search(pgStatPendingFunctions,
+                            (void *) &(srcent->functionid), HASH_REMOVE, NULL);
+            }
+        }    
+
+        /* destroy the hsah if no entry remains */
+        if (hash_get_num_entries(pgStatPendingFunctions) == 0)
+        {
+            hash_destroy(pgStatPendingFunctions);
+            pgStatPendingFunctions = NULL;
+        }
+    }
+
+    if (release_db)
+        dshash_release_lock(db_stats, dbentry);
+}
+
+static inline void
+pgstat_update_funcentry_by_backendstats(PgStat_StatFuncEntry *dest,
+                                        PgStat_BackendFunctionEntry *src,
+                                        bool init)
+{
+    if (init)
+    {
+        /*
+         * If it's a new function entry, initialize counters to the values
+         * we just got.
+         */
+        dest->f_numcalls = src->f_counts.f_numcalls;
+        dest->f_total_time =
+            INSTR_TIME_GET_MICROSEC(src->f_counts.f_total_time);
+        dest->f_self_time =
+            INSTR_TIME_GET_MICROSEC(src->f_counts.f_self_time);
+    }
+    else
+    {
+        /*
+         * Otherwise add the values to the existing entry.
+         */
+        dest->f_numcalls += src->f_counts.f_numcalls;
+        dest->f_total_time +=
+            INSTR_TIME_GET_MICROSEC(src->f_counts.f_total_time);
+        dest->f_self_time +=
+            INSTR_TIME_GET_MICROSEC(src->f_counts.f_self_time);
+    }
+}
+
+static inline void
+pgstat_update_funcentry_by_stats(PgStat_StatFuncEntry *dest,
+                                 PgStat_StatFuncEntry *src,
+                                 bool init)
+{
+    if (init)
+    {
+        /*
+         * If it's a new function entry, initialize counters to the values
+         * we just got.
+         */
+        dest->f_numcalls = src->f_numcalls;
+        dest->f_total_time = src->f_total_time;
+        dest->f_self_time = src->f_self_time;
+    }
+    else
+    {
+        /*
+         * Otherwise add the values to the existing entry.
+         */
+        dest->f_numcalls += src->f_numcalls;
+        dest->f_total_time += src->f_total_time;
+        dest->f_self_time += src->f_self_time;
+    }
+}
+
+
+
 /* ----------
  * pgstat_vacuum_stat() -
  *
@@ -1018,17 +1086,11 @@ void
 pgstat_vacuum_stat(void)
 {
     HTAB       *oidtab;
-    PgStat_MsgTabpurge msg;
-    PgStat_MsgFuncpurge f_msg;
     dshash_table *dshtable;
     dshash_seq_status dshstat;
     PgStat_StatDBEntry *dbentry;
     PgStat_StatTabEntry *tabentry;
     PgStat_StatFuncEntry *funcentry;
-    int            len;
-
-    if (pgStatSock == PGINVALID_SOCKET)
-        return;
 
     /* If not done for this transaction, take a snapshot of stats */
     if (!backend_snapshot_global_stats())
@@ -1044,7 +1106,7 @@ pgstat_vacuum_stat(void)
      * collector to drop them.
      */
 
-    dshash_seq_init(&dshstat, db_stats, true);
+    dshash_seq_init(&dshstat, db_stats, true, true);
     while ((dbentry = (PgStat_StatDBEntry *) dshash_seq_next(&dshstat)) != NULL)
     {
         Oid            dbid = dbentry->databaseid;
@@ -1063,8 +1125,8 @@ pgstat_vacuum_stat(void)
     /*
      * Lookup our own database entry; if not found, nothing more to do.
      */
-    dbentry = backend_get_db_entry(MyDatabaseId, true);
-    if (dbentry == NULL)
+    dbentry = pgstat_get_db_entry(MyDatabaseId, PGSTAT_TABLE_WRITE, NULL);
+    if (!dbentry)
         return;
     
     /*
@@ -1072,17 +1134,12 @@ pgstat_vacuum_stat(void)
      */
     oidtab = pgstat_collect_oids(RelationRelationId);
 
-    /*
-     * Initialize our messages table counter to zero
-     */
-    msg.m_nentries = 0;
-
     /*
      * Check for all tables listed in stats hashtable if they still exist.
      * Stats cache is useless here so directly search the shared hash.
      */
     dshtable = dshash_attach(area, &dsh_tblparams, dbentry->tables, 0);
-    dshash_seq_init(&dshstat, dshtable, false);
+    dshash_seq_init(&dshstat, dshtable, false, true);
     while ((tabentry = (PgStat_StatTabEntry *) dshash_seq_next(&dshstat)) != NULL)
     {
         Oid            tabid = tabentry->tableid;
@@ -1092,41 +1149,11 @@ pgstat_vacuum_stat(void)
         if (hash_search(oidtab, (void *) &tabid, HASH_FIND, NULL) != NULL)
             continue;
 
-        /*
-         * Not there, so add this table's Oid to the message
-         */
-        msg.m_tableid[msg.m_nentries++] = tabid;
-
-        /*
-         * If the message is full, send it out and reinitialize to empty
-         */
-        if (msg.m_nentries >= PGSTAT_NUM_TABPURGE)
-        {
-            len = offsetof(PgStat_MsgTabpurge, m_tableid[0])
-                + msg.m_nentries * sizeof(Oid);
-
-            pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_TABPURGE);
-            msg.m_databaseid = MyDatabaseId;
-            pgstat_send(&msg, len);
-
-            msg.m_nentries = 0;
-        }
+        /* Not there, so purge this table */
+        dshash_delete_entry(dshtable, tabentry);
     }
     dshash_detach(dshtable);
 
-    /*
-     * Send the rest
-     */
-    if (msg.m_nentries > 0)
-    {
-        len = offsetof(PgStat_MsgTabpurge, m_tableid[0])
-            + msg.m_nentries * sizeof(Oid);
-
-        pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_TABPURGE);
-        msg.m_databaseid = MyDatabaseId;
-        pgstat_send(&msg, len);
-    }
-
     /* Clean up */
     hash_destroy(oidtab);
 
@@ -1139,11 +1166,7 @@ pgstat_vacuum_stat(void)
     {
         oidtab = pgstat_collect_oids(ProcedureRelationId);
 
-        pgstat_setheader(&f_msg.m_hdr, PGSTAT_MTYPE_FUNCPURGE);
-        f_msg.m_databaseid = MyDatabaseId;
-        f_msg.m_nentries = 0;
-
-        dshash_seq_init(&dshstat, dshtable, false);
+        dshash_seq_init(&dshstat, dshtable, false, true);
         while ((funcentry = (PgStat_StatFuncEntry *) dshash_seq_next(&dshstat)) != NULL)
         {
             Oid            funcid = funcentry->functionid;
@@ -1153,39 +1176,14 @@ pgstat_vacuum_stat(void)
             if (hash_search(oidtab, (void *) &funcid, HASH_FIND, NULL) != NULL)
                 continue;
 
-            /*
-             * Not there, so add this function's Oid to the message
-             */
-            f_msg.m_functionid[f_msg.m_nentries++] = funcid;
-
-            /*
-             * If the message is full, send it out and reinitialize to empty
-             */
-            if (f_msg.m_nentries >= PGSTAT_NUM_FUNCPURGE)
-            {
-                len = offsetof(PgStat_MsgFuncpurge, m_functionid[0])
-                    + f_msg.m_nentries * sizeof(Oid);
-
-                pgstat_send(&f_msg, len);
-
-                f_msg.m_nentries = 0;
-            }
-        }
-
-        /*
-         * Send the rest
-         */
-        if (f_msg.m_nentries > 0)
-        {
-            len = offsetof(PgStat_MsgFuncpurge, m_functionid[0])
-                + f_msg.m_nentries * sizeof(Oid);
-
-            pgstat_send(&f_msg, len);
+            /* Not there, so remove this function */
+            dshash_delete_entry(dshtable, funcentry);
         }
 
         hash_destroy(oidtab);
     }
     dshash_detach(dshtable);
+    dshash_release_lock(db_stats, dbentry);
 }
 
 
@@ -1240,57 +1238,50 @@ pgstat_collect_oids(Oid catalogid)
  * pgstat_drop_database() -
  *
  *    Tell the collector that we just dropped a database.
- *    (If the message gets lost, we will still clean the dead DB eventually
- *    via future invocations of pgstat_vacuum_stat().)
+ *  (If some stats update happens after this, this entry will re-created but
+ *    we will still clean the dead DB eventually via future invocations of
+ *    pgstat_vacuum_stat().)
  * ----------
  */
+
 void
 pgstat_drop_database(Oid databaseid)
 {
-    PgStat_MsgDropdb msg;
+    PgStat_StatDBEntry *dbentry;
 
-    if (pgStatSock == PGINVALID_SOCKET)
+    Assert (OidIsValid(databaseid));
+
+    if (db_stats == NULL)
         return;
 
-    pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_DROPDB);
-    msg.m_databaseid = databaseid;
-    pgstat_send(&msg, sizeof(msg));
+    /*
+     * Lookup the database in the hashtable with exclusive lock.
+     */
+    dbentry = pgstat_get_db_entry(databaseid, PGSTAT_TABLE_WRITE, NULL);
+
+    /*
+     * If found, remove it (along with the db statfile).
+     */
+    if (dbentry)
+    {
+        if (dbentry->tables != DSM_HANDLE_INVALID)
+        {
+            dshash_table *tbl =
+                dshash_attach(area, &dsh_tblparams, dbentry->tables, 0);
+            dshash_destroy(tbl);
+        }
+        if (dbentry->functions != DSM_HANDLE_INVALID)
+        {
+            dshash_table *tbl =
+                dshash_attach(area, &dsh_funcparams, dbentry->functions, 0);
+            dshash_destroy(tbl);
+        }
+
+        dshash_delete_entry(db_stats, (void *)dbentry);
+    }
 }
 
 
-/* ----------
- * pgstat_drop_relation() -
- *
- *    Tell the collector that we just dropped a relation.
- *    (If the message gets lost, we will still clean the dead entry eventually
- *    via future invocations of pgstat_vacuum_stat().)
- *
- *    Currently not used for lack of any good place to call it; we rely
- *    entirely on pgstat_vacuum_stat() to clean out stats for dead rels.
- * ----------
- */
-#ifdef NOT_USED
-void
-pgstat_drop_relation(Oid relid)
-{
-    PgStat_MsgTabpurge msg;
-    int            len;
-
-    if (pgStatSock == PGINVALID_SOCKET)
-        return;
-
-    msg.m_tableid[0] = relid;
-    msg.m_nentries = 1;
-
-    len = offsetof(PgStat_MsgTabpurge, m_tableid[0]) + sizeof(Oid);
-
-    pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_TABPURGE);
-    msg.m_databaseid = MyDatabaseId;
-    pgstat_send(&msg, len);
-}
-#endif                            /* NOT_USED */
-
-
 /* ----------
  * pgstat_reset_counters() -
  *
@@ -1303,14 +1294,46 @@ pgstat_drop_relation(Oid relid)
 void
 pgstat_reset_counters(void)
 {
-    PgStat_MsgResetcounter msg;
+    PgStat_StatDBEntry           *dbentry;
+    pg_stat_table_result_status status;
 
-    if (pgStatSock == PGINVALID_SOCKET)
+    if (db_stats == NULL)
         return;
 
-    pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_RESETCOUNTER);
-    msg.m_databaseid = MyDatabaseId;
-    pgstat_send(&msg, sizeof(msg));
+    /*
+     * Lookup the database in the hashtable.  Nothing to do if not there.
+     */
+    dbentry = pgstat_get_db_entry(MyDatabaseId, PGSTAT_TABLE_WRITE, &status);
+
+    if (!dbentry)
+        return;
+
+    /*
+     * We simply throw away all the database's table entries by recreating a
+     * new hash table for them.
+     */
+    if (dbentry->tables != DSM_HANDLE_INVALID)
+    {
+        dshash_table *t =
+            dshash_attach(area, &dsh_tblparams, dbentry->tables, 0);
+        dshash_destroy(t);
+        dbentry->tables = DSM_HANDLE_INVALID;
+    }
+    if (dbentry->functions != DSM_HANDLE_INVALID)
+    {
+        dshash_table *t =
+            dshash_attach(area, &dsh_funcparams, dbentry->functions, 0);
+        dshash_destroy(t);
+        dbentry->functions = DSM_HANDLE_INVALID;
+    }
+
+    /*
+     * Reset database-level stats, too.  This creates empty hash tables for
+     * tables and functions.
+     */
+    reset_dbentry_counters(dbentry);
+
+    dshash_release_lock(db_stats, dbentry);
 }
 
 /* ----------
@@ -1325,23 +1348,32 @@ pgstat_reset_counters(void)
 void
 pgstat_reset_shared_counters(const char *target)
 {
-    PgStat_MsgResetsharedcounter msg;
-
-    if (pgStatSock == PGINVALID_SOCKET)
+    if (db_stats == NULL)
         return;
 
+    /* Reset the archiver statistics for the cluster. */
     if (strcmp(target, "archiver") == 0)
-        msg.m_resettarget = RESET_ARCHIVER;
+    {
+        LWLockAcquire(StatsLock, LW_EXCLUSIVE);
+
+        memset(&shared_archiverStats, 0, sizeof(shared_archiverStats));
+        shared_archiverStats->stat_reset_timestamp = GetCurrentTimestamp();
+    }
     else if (strcmp(target, "bgwriter") == 0)
-        msg.m_resettarget = RESET_BGWRITER;
+    {
+        LWLockAcquire(StatsLock, LW_EXCLUSIVE);
+
+        /* Reset the global background writer statistics for the cluster. */
+        memset(&shared_globalStats, 0, sizeof(shared_globalStats));
+        shared_globalStats->stat_reset_timestamp = GetCurrentTimestamp();
+    }
     else
         ereport(ERROR,
                 (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
                  errmsg("unrecognized reset target: \"%s\"", target),
                  errhint("Target must be \"archiver\" or \"bgwriter\".")));
-
-    pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_RESETSHAREDCOUNTER);
-    pgstat_send(&msg, sizeof(msg));
+    
+    LWLockRelease(StatsLock);
 }
 
 /* ----------
@@ -1356,17 +1388,38 @@ pgstat_reset_shared_counters(const char *target)
 void
 pgstat_reset_single_counter(Oid objoid, PgStat_Single_Reset_Type type)
 {
-    PgStat_MsgResetsinglecounter msg;
+    PgStat_StatDBEntry *dbentry;
+    
 
-    if (pgStatSock == PGINVALID_SOCKET)
+    /* Don't defer */
+
+    if (db_stats == NULL)
         return;
 
-    pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_RESETSINGLECOUNTER);
-    msg.m_databaseid = MyDatabaseId;
-    msg.m_resettype = type;
-    msg.m_objectid = objoid;
+    dbentry = pgstat_get_db_entry(MyDatabaseId, PGSTAT_TABLE_WRITE, NULL);
 
-    pgstat_send(&msg, sizeof(msg));
+    if (!dbentry)
+        return;
+
+    /* Set the reset timestamp for the whole database */
+    dbentry->stat_reset_timestamp = GetCurrentTimestamp();
+
+    /* Remove object if it exists, ignore it if not */
+    if (type == RESET_TABLE)
+    {
+        dshash_table *t =
+            dshash_attach(area, &dsh_tblparams, dbentry->tables, 0);
+        dshash_delete_key(t, (void *) &objoid);
+    }
+
+    if (type == RESET_FUNCTION)
+    {
+        dshash_table *t =
+            dshash_attach(area, &dsh_funcparams, dbentry->functions, 0);
+        dshash_delete_key(t, (void *) &objoid);
+    }
+
+    dshash_release_lock(db_stats, dbentry);
 }
 
 /* ----------
@@ -1380,16 +1433,23 @@ pgstat_reset_single_counter(Oid objoid, PgStat_Single_Reset_Type type)
 void
 pgstat_report_autovac(Oid dboid)
 {
-    PgStat_MsgAutovacStart msg;
+    PgStat_StatDBEntry *dbentry;
 
-    if (pgStatSock == PGINVALID_SOCKET)
+    /* Don't defer */
+
+    if (db_stats == NULL)
         return;
 
-    pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_AUTOVAC_START);
-    msg.m_databaseid = dboid;
-    msg.m_start_time = GetCurrentTimestamp();
+    /*
+     * Store the last autovacuum time in the database's hashtable entry.
+     */
+    dbentry = pgstat_get_db_entry(dboid,
+                                  PGSTAT_TABLE_WRITE | PGSTAT_TABLE_CREATE,
+                                  NULL);
 
-    pgstat_send(&msg, sizeof(msg));
+    dbentry->last_autovac_time = GetCurrentTimestamp();
+
+    dshash_release_lock(db_stats, dbentry);
 }
 
 
@@ -1403,19 +1463,43 @@ void
 pgstat_report_vacuum(Oid tableoid, bool shared,
                      PgStat_Counter livetuples, PgStat_Counter deadtuples)
 {
-    PgStat_MsgVacuum msg;
+    Oid                    dboid;
+    PgStat_StatDBEntry *dbentry;
+    PgStat_StatTabEntry *tabentry;
+    dshash_table *table;
 
-    if (pgStatSock == PGINVALID_SOCKET || !pgstat_track_counts)
+    /* Don't defer */
+
+    if (db_stats == NULL || !pgstat_track_counts)
         return;
 
-    pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_VACUUM);
-    msg.m_databaseid = shared ? InvalidOid : MyDatabaseId;
-    msg.m_tableoid = tableoid;
-    msg.m_autovacuum = IsAutoVacuumWorkerProcess();
-    msg.m_vacuumtime = GetCurrentTimestamp();
-    msg.m_live_tuples = livetuples;
-    msg.m_dead_tuples = deadtuples;
-    pgstat_send(&msg, sizeof(msg));
+    dboid = shared ? InvalidOid : MyDatabaseId;
+
+    /*
+     * Store the data in the table's hashtable entry.
+     */
+    dbentry = pgstat_get_db_entry(dboid,
+                                  PGSTAT_TABLE_WRITE | PGSTAT_TABLE_CREATE,
+                                  NULL);
+    table = dshash_attach(area, &dsh_tblparams, dbentry->tables, 0);
+    tabentry = pgstat_get_tab_entry(table, tableoid, true);
+
+    tabentry->n_live_tuples = livetuples;
+    tabentry->n_dead_tuples = deadtuples;
+
+    if (IsAutoVacuumWorkerProcess())
+    {
+        tabentry->autovac_vacuum_timestamp = GetCurrentTimestamp();
+        tabentry->autovac_vacuum_count++;
+    }
+    else
+    {
+        tabentry->vacuum_timestamp = GetCurrentTimestamp();
+        tabentry->vacuum_count++;
+    }
+    dshash_release_lock(table, tabentry);
+    dshash_detach(table);
+    dshash_release_lock(db_stats, dbentry);
 }
 
 /* --------
@@ -1432,9 +1516,14 @@ pgstat_report_analyze(Relation rel,
                       PgStat_Counter livetuples, PgStat_Counter deadtuples,
                       bool resetcounter)
 {
-    PgStat_MsgAnalyze msg;
+    Oid                    dboid;
+    PgStat_StatDBEntry *dbentry;
+    PgStat_StatTabEntry *tabentry;
+    dshash_table *table;
 
-    if (pgStatSock == PGINVALID_SOCKET || !pgstat_track_counts)
+    /* Don't defer */
+
+    if (db_stats == NULL || !pgstat_track_counts)
         return;
 
     /*
@@ -1463,15 +1552,42 @@ pgstat_report_analyze(Relation rel,
         deadtuples = Max(deadtuples, 0);
     }
 
-    pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_ANALYZE);
-    msg.m_databaseid = rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId;
-    msg.m_tableoid = RelationGetRelid(rel);
-    msg.m_autovacuum = IsAutoVacuumWorkerProcess();
-    msg.m_resetcounter = resetcounter;
-    msg.m_analyzetime = GetCurrentTimestamp();
-    msg.m_live_tuples = livetuples;
-    msg.m_dead_tuples = deadtuples;
-    pgstat_send(&msg, sizeof(msg));
+    dboid = rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId;
+
+    /*
+     * Store the data in the table's hashtable entry.
+     */
+    dbentry = pgstat_get_db_entry(dboid,
+                                  PGSTAT_TABLE_WRITE | PGSTAT_TABLE_CREATE,
+                                  NULL);
+
+    table = dshash_attach(area, &dsh_tblparams, dbentry->tables, 0);
+    tabentry = pgstat_get_tab_entry(table, RelationGetRelid(rel), true);
+
+    tabentry->n_live_tuples = livetuples;
+    tabentry->n_dead_tuples = deadtuples;
+
+    /*
+     * If commanded, reset changes_since_analyze to zero.  This forgets any
+     * changes that were committed while the ANALYZE was in progress, but we
+     * have no good way to estimate how many of those there were.
+     */
+    if (resetcounter)
+        tabentry->changes_since_analyze = 0;
+
+    if (IsAutoVacuumWorkerProcess())
+    {
+        tabentry->autovac_analyze_timestamp = GetCurrentTimestamp();
+        tabentry->autovac_analyze_count++;
+    }
+    else
+    {
+        tabentry->analyze_timestamp = GetCurrentTimestamp();
+        tabentry->analyze_count++;
+    }
+    dshash_release_lock(table, tabentry);
+    dshash_detach(table);
+    dshash_release_lock(db_stats, dbentry);
 }
 
 /* --------
@@ -1480,18 +1596,81 @@ pgstat_report_analyze(Relation rel,
  *    Tell the collector about a Hot Standby recovery conflict.
  * --------
  */
+static int pending_conflict_tablespace = 0;
+static int pending_conflict_lock = 0;
+static int pending_conflict_snapshot = 0;
+static int pending_conflict_bufferpin = 0;
+static int pending_conflict_startup_deadlock = 0;
+
 void
 pgstat_report_recovery_conflict(int reason)
 {
-    PgStat_MsgRecoveryConflict msg;
+    PgStat_StatDBEntry *dbentry;
+    pg_stat_table_result_status status;
 
-    if (pgStatSock == PGINVALID_SOCKET || !pgstat_track_counts)
+    pgstat_pending_recoveryconflict = false;
+
+    if (db_stats == NULL || !pgstat_track_counts)
         return;
 
-    pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_RECOVERYCONFLICT);
-    msg.m_databaseid = MyDatabaseId;
-    msg.m_reason = reason;
-    pgstat_send(&msg, sizeof(msg));
+    switch (reason)
+    {
+        case PROCSIG_RECOVERY_CONFLICT_DATABASE:
+
+            /*
+             * Since we drop the information about the database as soon as it
+             * replicates, there is no point in counting these conflicts.
+             */
+            break;
+        case PROCSIG_RECOVERY_CONFLICT_TABLESPACE:
+            pending_conflict_tablespace++;
+            break;
+        case PROCSIG_RECOVERY_CONFLICT_LOCK:
+            pending_conflict_lock++;
+            break;
+        case PROCSIG_RECOVERY_CONFLICT_SNAPSHOT:
+            pending_conflict_snapshot++;
+            break;
+        case PROCSIG_RECOVERY_CONFLICT_BUFFERPIN:
+            pending_conflict_bufferpin++;
+            break;
+        case PROCSIG_RECOVERY_CONFLICT_STARTUP_DEADLOCK:
+            pending_conflict_startup_deadlock++;
+            break;
+    }
+
+    dbentry = pgstat_get_db_entry(MyDatabaseId,
+                                  PGSTAT_TABLE_WRITE | PGSTAT_TABLE_CREATE |
+                                  PGSTAT_TABLE_NOWAIT,
+                                  &status);
+
+    if (status == PGSTAT_TABLE_LOCK_FAILED)
+    {
+        pgstat_pending_recoveryconflict = true;
+        return;
+    }
+
+    pgstat_cleanup_recovery_conflict(dbentry);
+
+    dshash_release_lock(db_stats, dbentry);
+}
+
+static void
+pgstat_cleanup_recovery_conflict(PgStat_StatDBEntry *dbentry)
+{
+    dbentry->n_conflict_tablespace    += pending_conflict_tablespace;
+    dbentry->n_conflict_lock         += pending_conflict_lock;
+    dbentry->n_conflict_snapshot    += pending_conflict_snapshot;
+    dbentry->n_conflict_bufferpin    += pending_conflict_bufferpin;
+    dbentry->n_conflict_startup_deadlock += pending_conflict_startup_deadlock;
+
+    pending_conflict_tablespace = 0;
+    pending_conflict_lock = 0;
+    pending_conflict_snapshot = 0;
+    pending_conflict_bufferpin = 0;
+    pending_conflict_startup_deadlock = 0;
+    
+    pgstat_pending_recoveryconflict = false;
 }
 
 /* --------
@@ -1500,17 +1679,38 @@ pgstat_report_recovery_conflict(int reason)
  *    Tell the collector about a deadlock detected.
  * --------
  */
+static int pending_deadlocks = 0;
+
 void
 pgstat_report_deadlock(void)
 {
-    PgStat_MsgDeadlock msg;
+    PgStat_StatDBEntry *dbentry;
+    pg_stat_table_result_status status;
 
-    if (pgStatSock == PGINVALID_SOCKET || !pgstat_track_counts)
+    if (db_stats == NULL || !pgstat_track_counts)
         return;
 
-    pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_DEADLOCK);
-    msg.m_databaseid = MyDatabaseId;
-    pgstat_send(&msg, sizeof(msg));
+    pending_deadlocks++;
+    pgstat_pending_deadlock = true;
+
+    dbentry = pgstat_get_db_entry(MyDatabaseId,
+                                  PGSTAT_TABLE_WRITE | PGSTAT_TABLE_CREATE |
+                                  PGSTAT_TABLE_NOWAIT,
+                                  &status);
+
+    if (status == PGSTAT_TABLE_LOCK_FAILED)
+        return;
+
+    pgstat_cleanup_deadlock(dbentry);
+    dshash_release_lock(db_stats, dbentry);
+    pgstat_pending_deadlock = false;
+}
+
+static void
+pgstat_cleanup_deadlock(PgStat_StatDBEntry *dbentry)
+{
+    dbentry->n_deadlocks += pending_deadlocks;
+    pending_deadlocks = 0;
 }
 
 /* --------
@@ -1519,40 +1719,51 @@ pgstat_report_deadlock(void)
  *    Tell the collector about a temporary file.
  * --------
  */
+static size_t pending_filesize = 0;
+static size_t pending_files = 0;
+
 void
 pgstat_report_tempfile(size_t filesize)
 {
-    PgStat_MsgTempFile msg;
+    PgStat_StatDBEntry *dbentry;
+    pg_stat_table_result_status status;
 
-    if (pgStatSock == PGINVALID_SOCKET || !pgstat_track_counts)
+    pgstat_pending_tempfile = false;
+    if (db_stats == NULL || !pgstat_track_counts)
         return;
 
-    pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_TEMPFILE);
-    msg.m_databaseid = MyDatabaseId;
-    msg.m_filesize = filesize;
-    pgstat_send(&msg, sizeof(msg));
+    if (filesize > 0) /* Is't there a case where filesize is really 0? */
+    {
+        pgstat_pending_tempfile = true;
+        pending_filesize += filesize; /* needs check overflow */
+        pending_files++;
+    }
+
+    dbentry = pgstat_get_db_entry(MyDatabaseId,
+                                  PGSTAT_TABLE_WRITE | PGSTAT_TABLE_CREATE |
+                                  PGSTAT_TABLE_NOWAIT,
+                                  &status);
+
+    if (status == PGSTAT_TABLE_LOCK_FAILED)
+        return;
+
+    pgstat_cleanup_tempfile(dbentry);
+
+    dshash_release_lock(db_stats, dbentry);
 }
 
-
-/* ----------
- * pgstat_ping() -
- *
- *    Send some junk data to the collector to increase traffic.
- * ----------
- */
-void
-pgstat_ping(void)
+static void
+pgstat_cleanup_tempfile(PgStat_StatDBEntry *dbentry)
 {
-    PgStat_MsgDummy msg;
 
-    if (pgStatSock == PGINVALID_SOCKET)
-        return;
+    dbentry->n_temp_bytes += pending_filesize;
+    dbentry->n_temp_files += pending_files;
+    pending_filesize = 0;
+    pending_files = 0;
+    pgstat_pending_tempfile = false;
 
-    pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_DUMMY);
-    pgstat_send(&msg, sizeof(msg));
 }
 
-
 /*
  * Initialize function call usage data.
  * Called by the executor before invoking a function.
@@ -1668,9 +1879,6 @@ pgstat_end_function_usage(PgStat_FunctionCallUsage *fcu, bool finalize)
         fs->f_numcalls++;
     fs->f_total_time = f_total;
     INSTR_TIME_ADD(fs->f_self_time, f_self);
-
-    /* indicate that we have something to send */
-    have_function_stats = true;
 }
 
 
@@ -1691,6 +1899,7 @@ pgstat_initstats(Relation rel)
 {
     Oid            rel_id = rel->rd_id;
     char        relkind = rel->rd_rel->relkind;
+    MemoryContext oldcontext;
 
     /* We only count stats for things that have storage */
     if (!(relkind == RELKIND_RELATION ||
@@ -1703,7 +1912,18 @@ pgstat_initstats(Relation rel)
         return;
     }
 
-    if (pgStatSock == PGINVALID_SOCKET || !pgstat_track_counts)
+    /* Attached shared memory lives for the process lifetime */
+    if (!IsUnderPostmaster)
+        return;
+
+    /* Attached shared memory lives for the process lifetime */
+    oldcontext = MemoryContextSwitchTo(TopMemoryContext);
+    while (!pgstat_attach_shared_stats())
+        sleep(1);
+
+    MemoryContextSwitchTo(oldcontext);
+
+    if (db_stats == NULL || !pgstat_track_counts)
     {
         /* We're not counting at all */
         rel->pgstat_info = NULL;
@@ -2353,26 +2573,6 @@ pgstat_twophase_postabort(TransactionId xid, uint16 info,
         rec->tuples_inserted + rec->tuples_updated;
 }
 
-
-/* ----------
- * pgstat_fetch_stat_dbentry() -
- *
- *    Support function for the SQL-callable pgstat* functions. Returns
- *    the collected statistics for one database or NULL. NULL doesn't mean
- *    that the database doesn't exist, it is just not yet known by the
- *    collector, so the caller is better off to report ZERO instead.
- * ----------
- */
-PgStat_StatDBEntry *
-pgstat_fetch_stat_dbentry(Oid dbid)
-{
-    PgStat_StatDBEntry *dbentry;
-
-    dbentry = backend_get_db_entry(dbid, false);
-    return dbentry;
-}
-
-
 /* ----------
  * pgstat_fetch_stat_tabentry() -
  *
@@ -2389,7 +2589,7 @@ pgstat_fetch_stat_tabentry(Oid relid)
     PgStat_StatTabEntry *tabentry;
 
     /* Lookup our database, then look in its table hash table. */
-    dbentry = backend_get_db_entry(MyDatabaseId, false);
+    dbentry = pgstat_fetch_stat_dbentry(MyDatabaseId, false);
     if (dbentry == NULL)
         return NULL;
 
@@ -2400,7 +2600,7 @@ pgstat_fetch_stat_tabentry(Oid relid)
     /*
      * If we didn't find it, maybe it's a shared table.
      */
-    dbentry = backend_get_db_entry(InvalidOid, false);
+    dbentry = pgstat_fetch_stat_dbentry(InvalidOid, false);
     if (dbentry == NULL)
         return NULL;
 
@@ -2426,7 +2626,7 @@ pgstat_fetch_stat_funcentry(Oid func_id)
     PgStat_StatFuncEntry *funcentry = NULL;
 
     /* Lookup our database, then find the requested function */
-    dbentry = pgstat_get_db_entry(MyDatabaseId, false);
+    dbentry = pgstat_get_db_entry(MyDatabaseId, PGSTAT_TABLE_READ, NULL);
     if (dbentry == NULL)
         return NULL;
 
@@ -2434,6 +2634,7 @@ pgstat_fetch_stat_funcentry(Oid func_id)
     if (funcentry == NULL)
         return NULL;
 
+    dshash_release_lock(db_stats, dbentry);
     return funcentry;
 }
 
@@ -2721,7 +2922,7 @@ pgstat_initialize(void)
     }
 
     /* Set up a process-exit hook to clean up */
-    on_shmem_exit(pgstat_beshutdown_hook, 0);
+    before_shmem_exit(pgstat_beshutdown_hook, 0);
 }
 
 /* ----------
@@ -2921,7 +3122,7 @@ pgstat_beshutdown_hook(int code, Datum arg)
      * during failed backend starts might never get counted.)
      */
     if (OidIsValid(MyDatabaseId))
-        pgstat_report_stat(true);
+        pgstat_update_stat(true);
 
     /*
      * Clear my status entry, following the protocol of bumping st_changecount
@@ -3188,7 +3389,8 @@ pgstat_read_current_status(void)
 #endif
     int            i;
 
-    Assert(!pgStatRunningInCollector);
+    Assert(IsUnderPostmaster);
+
     if (localBackendStatusTable)
         return;                    /* already done */
 
@@ -4105,96 +4307,76 @@ pgstat_get_backend_desc(BackendType backendType)
  * ------------------------------------------------------------
  */
 
-
 /* ----------
- * pgstat_setheader() -
+ * pgstat_update_archiver() -
  *
- *        Set common header fields in a statistics message
+ *    Update the stats data about the WAL file that we successfully archived or
+ *    failed to archive.
  * ----------
  */
-static void
-pgstat_setheader(PgStat_MsgHdr *hdr, StatMsgType mtype)
+void
+pgstat_update_archiver(const char *xlog, bool failed)
 {
-    hdr->m_type = mtype;
-}
-
-
-/* ----------
- * pgstat_send() -
- *
- *        Send out one statistics message to the collector
- * ----------
- */
-static void
-pgstat_send(void *msg, int len)
-{
-    int            rc;
-
-    if (pgStatSock == PGINVALID_SOCKET)
-        return;
-
-    ((PgStat_MsgHdr *) msg)->m_size = len;
-
-    /* We'll retry after EINTR, but ignore all other failures */
-    do
+    if (failed)
     {
-        rc = send(pgStatSock, msg, len, 0);
-    } while (rc < 0 && errno == EINTR);
-
-#ifdef USE_ASSERT_CHECKING
-    /* In debug builds, log send failures ... */
-    if (rc < 0)
-        elog(LOG, "could not send to statistics collector: %m");
-#endif
+        /* Failed archival attempt */
+        ++shared_archiverStats->failed_count;
+        memcpy(shared_archiverStats->last_failed_wal, xlog,
+               sizeof(shared_archiverStats->last_failed_wal));
+        shared_archiverStats->last_failed_timestamp = GetCurrentTimestamp();
+    }
+    else
+    {
+        /* Successful archival operation */
+        ++shared_archiverStats->archived_count;
+        memcpy(shared_archiverStats->last_archived_wal, xlog,
+               sizeof(shared_archiverStats->last_archived_wal));
+        shared_archiverStats->last_archived_timestamp = GetCurrentTimestamp();
+    }
 }
 
 /* ----------
- * pgstat_send_archiver() -
+ * pgstat_update_bgwriter() -
  *
- *    Tell the collector about the WAL file that we successfully
- *    archived or failed to archive.
+ *        Update bgwriter statistics
  * ----------
  */
 void
-pgstat_send_archiver(const char *xlog, bool failed)
-{
-    PgStat_MsgArchiver msg;
-
-    /*
-     * Prepare and send the message
-     */
-    pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_ARCHIVER);
-    msg.m_failed = failed;
-    StrNCpy(msg.m_xlog, xlog, sizeof(msg.m_xlog));
-    msg.m_timestamp = GetCurrentTimestamp();
-    pgstat_send(&msg, sizeof(msg));
-}
-
-/* ----------
- * pgstat_send_bgwriter() -
- *
- *        Send bgwriter statistics to the collector
- * ----------
- */
-void
-pgstat_send_bgwriter(void)
+pgstat_update_bgwriter(void)
 {
     /* We assume this initializes to zeroes */
-    static const PgStat_MsgBgWriter all_zeroes;
+    static const PgStat_BgWriter all_zeroes;
+
+    PgStat_BgWriter *s = &BgWriterStats;
+    MemoryContext oldcontext;
 
     /*
      * This function can be called even if nothing at all has happened. In
      * this case, avoid sending a completely empty message to the stats
      * collector.
      */
-    if (memcmp(&BgWriterStats, &all_zeroes, sizeof(PgStat_MsgBgWriter)) == 0)
+    if (memcmp(&BgWriterStats, &all_zeroes, sizeof(PgStat_BgWriter)) == 0)
         return;
 
-    /*
-     * Prepare and send the message
-     */
-    pgstat_setheader(&BgWriterStats.m_hdr, PGSTAT_MTYPE_BGWRITER);
-    pgstat_send(&BgWriterStats, sizeof(BgWriterStats));
+    /* Attached shared memory lives for the process lifetime */
+    oldcontext = MemoryContextSwitchTo(TopMemoryContext);
+    while (!pgstat_attach_shared_stats())
+        sleep(1);
+
+    MemoryContextSwitchTo(oldcontext);
+
+    LWLockAcquire(StatsLock, LW_EXCLUSIVE);
+    shared_globalStats->timed_checkpoints += s->timed_checkpoints;
+    shared_globalStats->requested_checkpoints += s->requested_checkpoints;
+    shared_globalStats->checkpoint_write_time += s->checkpoint_write_time;
+    shared_globalStats->checkpoint_sync_time += s->checkpoint_sync_time;
+    shared_globalStats->buf_written_checkpoints += s->buf_written_checkpoints;
+    shared_globalStats->buf_written_clean += s->buf_written_clean;
+    shared_globalStats->maxwritten_clean += s->maxwritten_clean;
+    shared_globalStats->buf_written_backend += s->buf_written_backend;
+    shared_globalStats->buf_fsync_backend += s->buf_fsync_backend;
+    shared_globalStats->buf_alloc += s->buf_alloc;
+    LWLockRelease(StatsLock);
 
     /*
      * Clear out the statistics buffer, so it can be re-used.
@@ -4215,8 +4397,6 @@ pgstat_send_bgwriter(void)
 void
 PgstatCollectorMain(void)
 {
-    int            len;
-    PgStat_Msg    msg;
     int            wr;
 
     /*
@@ -4272,164 +4452,17 @@ PgstatCollectorMain(void)
             break;
 
         /*
-         * Inner loop iterates as long as we keep getting messages, or until
-         * need_exit becomes set.
+         * Reload configuration if we got SIGHUP from the postmaster.
          */
-        while (!got_SIGTERM)
+        if (got_SIGHUP)
         {
-            /*
-             * Reload configuration if we got SIGHUP from the postmaster.
-             */
-            if (got_SIGHUP)
-            {
-                got_SIGHUP = false;
-                ProcessConfigFile(PGC_SIGHUP);
-            }
+            got_SIGHUP = false;
+            ProcessConfigFile(PGC_SIGHUP);
+        }
 
-            /*
-             * Try to receive and process a message.  This will not block,
-             * since the socket is set to non-blocking mode.
-             *
-             * XXX On Windows, we have to force pgwin32_recv to cooperate,
-             * despite the previous use of pg_set_noblock() on the socket.
-             * This is extremely broken and should be fixed someday.
-             */
-#ifdef WIN32
-            pgwin32_noblock = 1;
-#endif
-
-            len = recv(pgStatSock, (char *) &msg,
-                       sizeof(PgStat_Msg), 0);
-
-#ifdef WIN32
-            pgwin32_noblock = 0;
-#endif
-
-            if (len < 0)
-            {
-                if (errno == EAGAIN || errno == EWOULDBLOCK || errno == EINTR)
-                    break;        /* out of inner loop */
-                ereport(ERROR,
-                        (errcode_for_socket_access(),
-                         errmsg("could not read statistics message: %m")));
-            }
-
-            /*
-             * We ignore messages that are smaller than our common header
-             */
-            if (len < sizeof(PgStat_MsgHdr))
-                continue;
-
-            /*
-             * The received length must match the length in the header
-             */
-            if (msg.msg_hdr.m_size != len)
-                continue;
-
-            /*
-             * O.K. - we accept this message.  Process it.
-             */
-            switch (msg.msg_hdr.m_type)
-            {
-                case PGSTAT_MTYPE_DUMMY:
-                    break;
-
-                case PGSTAT_MTYPE_TABSTAT:
-                    pgstat_recv_tabstat((PgStat_MsgTabstat *) &msg, len);
-                    break;
-
-                case PGSTAT_MTYPE_TABPURGE:
-                    pgstat_recv_tabpurge((PgStat_MsgTabpurge *) &msg, len);
-                    break;
-
-                case PGSTAT_MTYPE_DROPDB:
-                    pgstat_recv_dropdb((PgStat_MsgDropdb *) &msg, len);
-                    break;
-
-                case PGSTAT_MTYPE_RESETCOUNTER:
-                    pgstat_recv_resetcounter((PgStat_MsgResetcounter *) &msg,
-                                             len);
-                    break;
-
-                case PGSTAT_MTYPE_RESETSHAREDCOUNTER:
-                    pgstat_recv_resetsharedcounter(
-                                                   (PgStat_MsgResetsharedcounter *) &msg,
-                                                   len);
-                    break;
-
-                case PGSTAT_MTYPE_RESETSINGLECOUNTER:
-                    pgstat_recv_resetsinglecounter(
-                                                   (PgStat_MsgResetsinglecounter *) &msg,
-                                                   len);
-                    break;
-
-                case PGSTAT_MTYPE_AUTOVAC_START:
-                    pgstat_recv_autovac((PgStat_MsgAutovacStart *) &msg, len);
-                    break;
-
-                case PGSTAT_MTYPE_VACUUM:
-                    pgstat_recv_vacuum((PgStat_MsgVacuum *) &msg, len);
-                    break;
-
-                case PGSTAT_MTYPE_ANALYZE:
-                    pgstat_recv_analyze((PgStat_MsgAnalyze *) &msg, len);
-                    break;
-
-                case PGSTAT_MTYPE_ARCHIVER:
-                    pgstat_recv_archiver((PgStat_MsgArchiver *) &msg, len);
-                    break;
-
-                case PGSTAT_MTYPE_BGWRITER:
-                    pgstat_recv_bgwriter((PgStat_MsgBgWriter *) &msg, len);
-                    break;
-
-                case PGSTAT_MTYPE_FUNCSTAT:
-                    pgstat_recv_funcstat((PgStat_MsgFuncstat *) &msg, len);
-                    break;
-
-                case PGSTAT_MTYPE_FUNCPURGE:
-                    pgstat_recv_funcpurge((PgStat_MsgFuncpurge *) &msg, len);
-                    break;
-
-                case PGSTAT_MTYPE_RECOVERYCONFLICT:
-                    pgstat_recv_recoveryconflict((PgStat_MsgRecoveryConflict *) &msg, len);
-                    break;
-
-                case PGSTAT_MTYPE_DEADLOCK:
-                    pgstat_recv_deadlock((PgStat_MsgDeadlock *) &msg, len);
-                    break;
-
-                case PGSTAT_MTYPE_TEMPFILE:
-                    pgstat_recv_tempfile((PgStat_MsgTempFile *) &msg, len);
-                    break;
-
-                default:
-                    break;
-            }
-        }                        /* end of inner message-processing loop */
-
-        /* Sleep until there's something to do */
-#ifndef WIN32
-        wr = WaitLatchOrSocket(MyLatch,
-                               WL_LATCH_SET | WL_POSTMASTER_DEATH | WL_SOCKET_READABLE,
-                               pgStatSock, -1L,
-                               WAIT_EVENT_PGSTAT_MAIN);
-#else
-
-        /*
-         * Windows, at least in its Windows Server 2003 R2 incarnation,
-         * sometimes loses FD_READ events.  Waking up and retrying the recv()
-         * fixes that, so don't sleep indefinitely.  This is a crock of the
-         * first water, but until somebody wants to debug exactly what's
-         * happening there, this is the best we can do.  The two-second
-         * timeout matches our pre-9.2 behavior.
-         */
-        wr = WaitLatchOrSocket(MyLatch,
-                               WL_LATCH_SET | WL_POSTMASTER_DEATH | WL_SOCKET_READABLE | WL_TIMEOUT,
-                               pgStatSock,
-                               2 * 1000L /* msec */ ,
-                               WAIT_EVENT_PGSTAT_MAIN);
-#endif
+        wr = WaitLatch(MyLatch,
+                       WL_LATCH_SET | WL_POSTMASTER_DEATH,
+                       -1L, WAIT_EVENT_PGSTAT_MAIN);
 
         /*
          * Emergency bailout if postmaster has died.  This is to avoid the
@@ -4552,29 +4585,62 @@ reset_dbentry_counters(PgStat_StatDBEntry *dbentry)
  * Else, return NULL.
  */
 static PgStat_StatDBEntry *
-pgstat_get_db_entry(Oid databaseid, bool create)
+pgstat_get_db_entry(Oid databaseid, int op,    pg_stat_table_result_status *status)
 {
     PgStat_StatDBEntry *result;
-    bool        found;
+    bool        nowait = ((op & PGSTAT_TABLE_NOWAIT) != 0);
+    bool        lock_acquired = true;
+    bool        found = true;
+    MemoryContext oldcontext;
 
-    Assert(pgStatRunningInCollector);
+    /* XXXXXXX */
+    oldcontext = MemoryContextSwitchTo(TopMemoryContext);
+    if (!pgstat_attach_shared_stats())
+    {
+        MemoryContextSwitchTo(oldcontext);
+        return false;
+    }
+    MemoryContextSwitchTo(oldcontext);
 
     /* Lookup or create the hash table entry for this database */
-    if (create)
+    if (op & PGSTAT_TABLE_CREATE)
+    {
         result = (PgStat_StatDBEntry *)
-            dshash_find_or_insert(db_stats,    &databaseid, &found);
+            dshash_find_or_insert_extended(db_stats, &databaseid,
+                                           &found, nowait);
+        if (result == NULL)
+            lock_acquired = false;
+        else if (!found)
+        {
+            /*
+             * If not found, initialize the new one.  This creates empty hash
+             * tables for tables and functions, too.
+             */
+            reset_dbentry_counters(result);
+        }
+    }
     else
-        result = (PgStat_StatDBEntry *)    dshash_find(db_stats, &databaseid, true);
+    {
+        result = (PgStat_StatDBEntry *)
+            dshash_find_extended(db_stats, &databaseid,
+                                 &lock_acquired, true, nowait);
+        if (result == NULL)
+            found = false;
+    }
 
-    if (!create)
-        return result;
-
-    /*
-     * If not found, initialize the new one.  This creates empty hash tables
-     * for tables and functions, too.
-     */
-    if (!found)
-        reset_dbentry_counters(result);
+    /* Set return status if requested */
+    if (status)
+    {
+        if (!lock_acquired)
+        {
+            Assert(nowait);
+            *status = PGSTAT_TABLE_LOCK_FAILED;
+        }
+        else if (!found)
+            *status = PGSTAT_TABLE_NOT_FOUND;
+        else
+            *status = PGSTAT_TABLE_FOUND;
+    }
 
     return result;
 }
@@ -4631,11 +4697,7 @@ pgstat_get_tab_entry(dshash_table *table, Oid tableoid, bool create)
 
 /* ----------
  * pgstat_write_statsfiles() -
- *        Write the global statistics file, as well as requested DB files.
- *
- *    When 'allDbs' is false, only the requested databases (listed in
- *    pending_write_requests) will be written; otherwise, all databases
- *    will be written.
+ *        Write the global statistics file, as well as DB files.
  * ----------
  */
 static void
@@ -4649,6 +4711,9 @@ pgstat_write_statsfiles(void)
     const char *statfile = PGSTAT_STAT_PERMANENT_FILENAME;
     int            rc;
 
+    /* should be called in stats collector  */
+    Assert(pgStatRunningInCollector);
+
     elog(DEBUG2, "writing stats file \"%s\"", statfile);
 
     /*
@@ -4691,7 +4756,7 @@ pgstat_write_statsfiles(void)
     /*
      * Walk through the database table.
      */
-    dshash_seq_init(&hstat, db_stats, false);
+    dshash_seq_init(&hstat, db_stats, false, false);
     while ((dbentry = (PgStat_StatDBEntry *) dshash_seq_next(&hstat)) != NULL)
     {
         /*
@@ -4744,13 +4809,6 @@ pgstat_write_statsfiles(void)
                         tmpfile, statfile)));
         unlink(tmpfile);
     }
-
-    /*
-     * Now throw away the list of requests.  Note that requests sent after we
-     * started the write are still waiting on the network socket.
-     */
-    list_free(pending_write_requests);
-    pending_write_requests = NIL;
 }
 
 /*
@@ -4797,6 +4855,8 @@ pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry)
     char        statfile[MAXPGPATH];
     dshash_table *tbl;
 
+    Assert(pgStatRunningInCollector);
+
     get_dbstat_filename(true, dbid, tmpfile, MAXPGPATH);
     get_dbstat_filename(false, dbid, statfile, MAXPGPATH);
 
@@ -4826,7 +4886,7 @@ pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry)
      * Walk through the database's access stats per table.
      */
     tbl = dshash_attach(area, &dsh_tblparams, dbentry->tables, 0);
-    dshash_seq_init(&tstat, tbl, false);
+    dshash_seq_init(&tstat, tbl, false, false);
     while ((tabentry = (PgStat_StatTabEntry *) dshash_seq_next(&tstat)) != NULL)
     {
         fputc('T', fpout);
@@ -4839,7 +4899,7 @@ pgstat_write_db_statsfile(PgStat_StatDBEntry *dbentry)
      * Walk through the database's function stats table.
      */
     tbl = dshash_attach(area, &dsh_funcparams, dbentry->functions, 0);
-    dshash_seq_init(&fstat, tbl, false);
+    dshash_seq_init(&fstat, tbl, false, false);
     while ((funcentry = (PgStat_StatFuncEntry *) dshash_seq_next(&fstat)) != NULL)
     {
         fputc('F', fpout);
@@ -4932,7 +4992,7 @@ pgstat_read_statsfiles(void)
     if ((fpin = AllocateFile(statfile, PG_BINARY_R)) == NULL)
     {
         if (errno != ENOENT)
-            ereport(pgStatRunningInCollector ? LOG : WARNING,
+            ereport(LOG,
                     (errcode_for_file_access(),
                      errmsg("could not open statistics file \"%s\": %m",
                             statfile)));
@@ -4945,7 +5005,7 @@ pgstat_read_statsfiles(void)
     if (fread(&format_id, 1, sizeof(format_id), fpin) != sizeof(format_id) ||
         format_id != PGSTAT_FILE_FORMAT_ID)
     {
-        ereport(pgStatRunningInCollector ? LOG : WARNING,
+        ereport(LOG,
                 (errmsg("corrupted statistics file \"%s\"", statfile)));
         goto done;
     }
@@ -4955,7 +5015,7 @@ pgstat_read_statsfiles(void)
      */
     if (fread(shared_globalStats, 1, sizeof(shared_globalStats), fpin) != sizeof(shared_globalStats))
     {
-        ereport(pgStatRunningInCollector ? LOG : WARNING,
+        ereport(LOG,
                 (errmsg("corrupted statistics file \"%s\"", statfile)));
         memset(shared_globalStats, 0, sizeof(*shared_globalStats));
         goto done;
@@ -4975,7 +5035,7 @@ pgstat_read_statsfiles(void)
      */
     if (fread(shared_archiverStats, 1, sizeof(shared_archiverStats), fpin) != sizeof(shared_archiverStats))
     {
-        ereport(pgStatRunningInCollector ? LOG : WARNING,
+        ereport(LOG,
                 (errmsg("corrupted statistics file \"%s\"", statfile)));
         memset(shared_archiverStats, 0, sizeof(*shared_archiverStats));
         goto done;
@@ -4997,7 +5057,7 @@ pgstat_read_statsfiles(void)
                 if (fread(&dbbuf, 1, offsetof(PgStat_StatDBEntry, tables),
                           fpin) != offsetof(PgStat_StatDBEntry, tables))
                 {
-                    ereport(pgStatRunningInCollector ? LOG : WARNING,
+                    ereport(LOG,
                             (errmsg("corrupted statistics file \"%s\"",
                                     statfile)));
                     goto done;
@@ -5012,7 +5072,7 @@ pgstat_read_statsfiles(void)
                 if (found)
                 {
                     dshash_release_lock(db_stats, dbentry);
-                    ereport(pgStatRunningInCollector ? LOG : WARNING,
+                    ereport(LOG,
                             (errmsg("corrupted statistics file \"%s\"",
                                     statfile)));
                     goto done;
@@ -5021,6 +5081,8 @@ pgstat_read_statsfiles(void)
                 memcpy(dbentry, &dbbuf, sizeof(PgStat_StatDBEntry));
                 dbentry->tables = DSM_HANDLE_INVALID;
                 dbentry->functions = DSM_HANDLE_INVALID;
+                dbentry->snapshot_tables = NULL;
+                dbentry->snapshot_functions = NULL;
 
                 /*
                  * In the collector, disregard the timestamp we read from the
@@ -5028,7 +5090,6 @@ pgstat_read_statsfiles(void)
                  * stats file immediately upon the first request from any
                  * backend.
                  */
-                Assert(pgStatRunningInCollector);
                 dbentry->stats_timestamp = 0;
 
                 /*
@@ -5051,7 +5112,7 @@ pgstat_read_statsfiles(void)
                 goto done;
 
             default:
-                ereport(pgStatRunningInCollector ? LOG : WARNING,
+                ereport(LOG,
                         (errmsg("corrupted statistics file \"%s\"",
                                 statfile)));
                 goto done;
@@ -5127,7 +5188,7 @@ pgstat_read_db_statsfile(Oid databaseid,
     if ((fpin = AllocateFile(statfile, PG_BINARY_R)) == NULL)
     {
         if (errno != ENOENT)
-            ereport(pgStatRunningInCollector ? LOG : WARNING,
+            ereport(LOG,
                     (errcode_for_file_access(),
                      errmsg("could not open statistics file \"%s\": %m",
                             statfile)));
@@ -5140,7 +5201,7 @@ pgstat_read_db_statsfile(Oid databaseid,
     if (fread(&format_id, 1, sizeof(format_id), fpin) != sizeof(format_id) ||
         format_id != PGSTAT_FILE_FORMAT_ID)
     {
-        ereport(pgStatRunningInCollector ? LOG : WARNING,
+        ereport(LOG,
                 (errmsg("corrupted statistics file \"%s\"", statfile)));
         goto done;
     }
@@ -5160,7 +5221,7 @@ pgstat_read_db_statsfile(Oid databaseid,
                 if (fread(&tabbuf, 1, sizeof(PgStat_StatTabEntry),
                           fpin) != sizeof(PgStat_StatTabEntry))
                 {
-                    ereport(pgStatRunningInCollector ? LOG : WARNING,
+                    ereport(LOG,
                             (errmsg("corrupted statistics file \"%s\"",
                                     statfile)));
                     goto done;
@@ -5179,7 +5240,7 @@ pgstat_read_db_statsfile(Oid databaseid,
                 if (found)
                 {
                     dshash_release_lock(tabhash, tabentry);
-                    ereport(pgStatRunningInCollector ? LOG : WARNING,
+                    ereport(LOG,
                             (errmsg("corrupted statistics file \"%s\"",
                                     statfile)));
                     goto done;
@@ -5196,7 +5257,7 @@ pgstat_read_db_statsfile(Oid databaseid,
                 if (fread(&funcbuf, 1, sizeof(PgStat_StatFuncEntry),
                           fpin) != sizeof(PgStat_StatFuncEntry))
                 {
-                    ereport(pgStatRunningInCollector ? LOG : WARNING,
+                    ereport(LOG,
                             (errmsg("corrupted statistics file \"%s\"",
                                     statfile)));
                     goto done;
@@ -5214,7 +5275,7 @@ pgstat_read_db_statsfile(Oid databaseid,
 
                 if (found)
                 {
-                    ereport(pgStatRunningInCollector ? LOG : WARNING,
+                    ereport(LOG,
                             (errmsg("corrupted statistics file \"%s\"",
                                     statfile)));
                     goto done;
@@ -5231,7 +5292,7 @@ pgstat_read_db_statsfile(Oid databaseid,
                 goto done;
 
             default:
-                ereport(pgStatRunningInCollector ? LOG : WARNING,
+                ereport(LOG,
                         (errmsg("corrupted statistics file \"%s\"",
                                 statfile)));
                 goto done;
@@ -5439,7 +5500,7 @@ snapshot_statentry_all(const char *hashname,
     dest = create_local_stats_hash(hashname,
                                     keysize, entrysize, num_entries);
 
-    dshash_seq_init(&s, t, true);
+    dshash_seq_init(&s, t, true, false);
     while ((ps = dshash_seq_next(&s)) != NULL)
     {
         bool found;
@@ -5473,8 +5534,6 @@ backend_snapshot_global_stats(void)
     if (snapshot_globalStats)
         return true;
 
-    Assert(!pgStatRunningInCollector);
-
     /* Attached shared memory lives for the process lifetime */
     oldcontext = MemoryContextSwitchTo(TopMemoryContext);
     if (!pgstat_attach_shared_stats())
@@ -5519,25 +5578,31 @@ backend_snapshot_global_stats(void)
 }
 
 /* ----------
- * backend_get_db_entry() -
+ * pgstat_fetch_stat_dbentry() -
  *
  *    Find database stats entry on backends. The returned entries are cached
  *    until transaction end. If onshot is true, they are not cached and returned
  *    in a palloc'ed memory.
  */
 PgStat_StatDBEntry *
-backend_get_db_entry(Oid dbid, bool oneshot)
+pgstat_fetch_stat_dbentry(Oid dbid, bool oneshot)
 {
     /* take a local snapshot if we don't have one */
     char *hashname = "local database stats hash";
+    PgStat_StatDBEntry *dbentry;
+
+    /* should be called from backends  */
+    Assert(IsUnderPostmaster);
 
     /* If not done for this transaction, take a snapshot of global stats */
     if (!backend_snapshot_global_stats())
         return NULL;
 
-    return snapshot_statentry(oneshot ? NULL : &snapshot_db_stats,
-                              hashname, db_stats, 0, &dsh_dbparams,
-                              dbid);
+    dbentry = snapshot_statentry(oneshot ? NULL : &snapshot_db_stats,
+                                 hashname, db_stats, 0, &dsh_dbparams,
+                                 dbid);
+    
+    return dbentry;
 }
 
 /* ----------
@@ -5551,6 +5616,9 @@ backend_snapshot_all_db_entries(void)
     /* take a local snapshot if we don't have one */
     char *hashname = "local database stats hash";
 
+    /* should be called from backends  */
+    Assert(IsUnderPostmaster);
+
     /* If not done for this transaction, take a snapshot of global stats */
     if (!backend_snapshot_global_stats())
         return NULL;
@@ -5570,6 +5638,10 @@ backend_get_tab_entry(PgStat_StatDBEntry *dbent, Oid reloid, bool oneshot)
 {
     /* take a local snapshot if we don't have one */
     char *hashname = "local table stats hash";
+
+    /* should be called from backends  */
+    Assert(IsUnderPostmaster);
+
     return snapshot_statentry(oneshot ? NULL : &dbent->snapshot_tables,
                               hashname, NULL, dbent->tables, &dsh_tblparams,
                               reloid);
@@ -5586,6 +5658,10 @@ static PgStat_StatFuncEntry *
 backend_get_func_etnry(PgStat_StatDBEntry *dbent, Oid funcid, bool oneshot)
 {
     char *hashname = "local table stats hash";
+
+    /* should be called from backends  */
+    Assert(IsUnderPostmaster);
+
     return snapshot_statentry(oneshot ? NULL : &dbent->snapshot_tables,
                               hashname, NULL, dbent->functions, &dsh_funcparams,
                               funcid);
@@ -5640,627 +5716,103 @@ pgstat_clear_snapshot(void)
 }
 
 
-/* ----------
- * pgstat_recv_tabstat() -
- *
- *    Count what the backend has done.
- * ----------
- */
-static void
-pgstat_recv_tabstat(PgStat_MsgTabstat *msg, int len)
+static bool
+pgstat_update_tabentry(dshash_table *tabhash, PgStat_TableStatus *stat,
+                       bool nowait)
 {
-    dshash_table *tabhash;
-    PgStat_StatDBEntry *dbentry;
     PgStat_StatTabEntry *tabentry;
-    int            i;
-    bool        found;
+    bool    found;
 
-    dbentry = pgstat_get_db_entry(msg->m_databaseid, true);
+    if (tabhash == NULL)
+        return false;
 
-    /*
-     * Update database-wide stats.
-     */
-    dbentry->n_xact_commit += (PgStat_Counter) (msg->m_xact_commit);
-    dbentry->n_xact_rollback += (PgStat_Counter) (msg->m_xact_rollback);
-    dbentry->n_block_read_time += msg->m_block_read_time;
-    dbentry->n_block_write_time += msg->m_block_write_time;
+    tabentry = (PgStat_StatTabEntry *)
+        dshash_find_or_insert_extended(tabhash, (void *) &(stat->t_id),
+                                       &found, nowait);
 
-    tabhash = dshash_attach(area, &dsh_tblparams, dbentry->tables, 0);
-    /*
-     * Process all table entries in the message.
-     */
-    for (i = 0; i < msg->m_nentries; i++)
+    /* failed to acquire lock */
+    if (tabentry == NULL)
+        return false;
+
+    if (!found)
     {
-        PgStat_TableEntry *tabmsg = &(msg->m_entry[i]);
-
-        tabentry = (PgStat_StatTabEntry *)
-            dshash_find_or_insert(tabhash, (void *) &(tabmsg->t_id), &found);
-
-        if (!found)
-        {
-            /*
-             * If it's a new table entry, initialize counters to the values we
-             * just got.
-             */
-            tabentry->numscans = tabmsg->t_counts.t_numscans;
-            tabentry->tuples_returned = tabmsg->t_counts.t_tuples_returned;
-            tabentry->tuples_fetched = tabmsg->t_counts.t_tuples_fetched;
-            tabentry->tuples_inserted = tabmsg->t_counts.t_tuples_inserted;
-            tabentry->tuples_updated = tabmsg->t_counts.t_tuples_updated;
-            tabentry->tuples_deleted = tabmsg->t_counts.t_tuples_deleted;
-            tabentry->tuples_hot_updated = tabmsg->t_counts.t_tuples_hot_updated;
-            tabentry->n_live_tuples = tabmsg->t_counts.t_delta_live_tuples;
-            tabentry->n_dead_tuples = tabmsg->t_counts.t_delta_dead_tuples;
-            tabentry->changes_since_analyze = tabmsg->t_counts.t_changed_tuples;
-            tabentry->blocks_fetched = tabmsg->t_counts.t_blocks_fetched;
-            tabentry->blocks_hit = tabmsg->t_counts.t_blocks_hit;
-
-            tabentry->vacuum_timestamp = 0;
-            tabentry->vacuum_count = 0;
-            tabentry->autovac_vacuum_timestamp = 0;
-            tabentry->autovac_vacuum_count = 0;
-            tabentry->analyze_timestamp = 0;
-            tabentry->analyze_count = 0;
-            tabentry->autovac_analyze_timestamp = 0;
-            tabentry->autovac_analyze_count = 0;
-        }
-        else
-        {
-            /*
-             * Otherwise add the values to the existing entry.
-             */
-            tabentry->numscans += tabmsg->t_counts.t_numscans;
-            tabentry->tuples_returned += tabmsg->t_counts.t_tuples_returned;
-            tabentry->tuples_fetched += tabmsg->t_counts.t_tuples_fetched;
-            tabentry->tuples_inserted += tabmsg->t_counts.t_tuples_inserted;
-            tabentry->tuples_updated += tabmsg->t_counts.t_tuples_updated;
-            tabentry->tuples_deleted += tabmsg->t_counts.t_tuples_deleted;
-            tabentry->tuples_hot_updated += tabmsg->t_counts.t_tuples_hot_updated;
-            /* If table was truncated, first reset the live/dead counters */
-            if (tabmsg->t_counts.t_truncated)
-            {
-                tabentry->n_live_tuples = 0;
-                tabentry->n_dead_tuples = 0;
-            }
-            tabentry->n_live_tuples += tabmsg->t_counts.t_delta_live_tuples;
-            tabentry->n_dead_tuples += tabmsg->t_counts.t_delta_dead_tuples;
-            tabentry->changes_since_analyze += tabmsg->t_counts.t_changed_tuples;
-            tabentry->blocks_fetched += tabmsg->t_counts.t_blocks_fetched;
-            tabentry->blocks_hit += tabmsg->t_counts.t_blocks_hit;
-        }
-
-        /* Clamp n_live_tuples in case of negative delta_live_tuples */
-        tabentry->n_live_tuples = Max(tabentry->n_live_tuples, 0);
-        /* Likewise for n_dead_tuples */
-        tabentry->n_dead_tuples = Max(tabentry->n_dead_tuples, 0);
-        dshash_release_lock(tabhash, tabentry);
-
         /*
-         * Add per-table stats to the per-database entry, too.
+         * If it's a new table entry, initialize counters to the values we
+         * just got.
          */
-        dbentry->n_tuples_returned += tabmsg->t_counts.t_tuples_returned;
-        dbentry->n_tuples_fetched += tabmsg->t_counts.t_tuples_fetched;
-        dbentry->n_tuples_inserted += tabmsg->t_counts.t_tuples_inserted;
-        dbentry->n_tuples_updated += tabmsg->t_counts.t_tuples_updated;
-        dbentry->n_tuples_deleted += tabmsg->t_counts.t_tuples_deleted;
-        dbentry->n_blocks_fetched += tabmsg->t_counts.t_blocks_fetched;
-        dbentry->n_blocks_hit += tabmsg->t_counts.t_blocks_hit;
-    }
+        tabentry->numscans = stat->t_counts.t_numscans;
+        tabentry->tuples_returned = stat->t_counts.t_tuples_returned;
+        tabentry->tuples_fetched = stat->t_counts.t_tuples_fetched;
+        tabentry->tuples_inserted = stat->t_counts.t_tuples_inserted;
+        tabentry->tuples_updated = stat->t_counts.t_tuples_updated;
+        tabentry->tuples_deleted = stat->t_counts.t_tuples_deleted;
+        tabentry->tuples_hot_updated = stat->t_counts.t_tuples_hot_updated;
+        tabentry->n_live_tuples = stat->t_counts.t_delta_live_tuples;
+        tabentry->n_dead_tuples = stat->t_counts.t_delta_dead_tuples;
+        tabentry->changes_since_analyze = stat->t_counts.t_changed_tuples;
+        tabentry->blocks_fetched = stat->t_counts.t_blocks_fetched;
+        tabentry->blocks_hit = stat->t_counts.t_blocks_hit;
 
-    dshash_release_lock(db_stats, dbentry);
-}
-
-
-/* ----------
- * pgstat_recv_tabpurge() -
- *
- *    Arrange for dead table removal.
- * ----------
- */
-static void
-pgstat_recv_tabpurge(PgStat_MsgTabpurge *msg, int len)
-{
-    dshash_table *tbl;
-    PgStat_StatDBEntry *dbentry;
-    int            i;
-
-    dbentry = pgstat_get_db_entry(msg->m_databaseid, false);
-    /*
-     * No need to purge if we don't even know the database.
-     */
-    if (!dbentry || dbentry->tables == DSM_HANDLE_INVALID)
-    {
-        if (dbentry)
-            dshash_release_lock(db_stats, dbentry);
-        return;
-    }
-
-    tbl = dshash_attach(area, &dsh_tblparams, dbentry->tables, 0);
-    /*
-     * Process all table entries in the message.
-     */
-    for (i = 0; i < msg->m_nentries; i++)
-    {
-        /* Remove from hashtable if present; we don't care if it's not. */
-        (void) dshash_delete_key(tbl, (void *) &(msg->m_tableid[i]));
-    }
-
-    dshash_release_lock(db_stats, dbentry);
-
-}
-
-
-/* ----------
- * pgstat_recv_dropdb() -
- *
- *    Arrange for dead database removal
- * ----------
- */
-static void
-pgstat_recv_dropdb(PgStat_MsgDropdb *msg, int len)
-{
-    Oid            dbid = msg->m_databaseid;
-    PgStat_StatDBEntry *dbentry;
-
-    /*
-     * Lookup the database in the hashtable.
-     */
-    dbentry = pgstat_get_db_entry(dbid, false);
-
-    /*
-     * If found, remove it (along with the db statfile).
-     */
-    if (dbentry)
-    {
-        if (dbentry->tables != DSM_HANDLE_INVALID)
-        {
-            dshash_table *tbl =
-                dshash_attach(area, &dsh_tblparams, dbentry->tables, 0);
-            dshash_destroy(tbl);
-        }
-        if (dbentry->functions != DSM_HANDLE_INVALID)
-        {
-            dshash_table *tbl =
-                dshash_attach(area, &dsh_funcparams, dbentry->functions, 0);
-            dshash_destroy(tbl);
-        }
-
-        dshash_delete_entry(db_stats, (void *)dbentry);
-    }
-}
-
-
-/* ----------
- * pgstat_recv_resetcounter() -
- *
- *    Reset the statistics for the specified database.
- * ----------
- */
-static void
-pgstat_recv_resetcounter(PgStat_MsgResetcounter *msg, int len)
-{
-    PgStat_StatDBEntry *dbentry;
-
-    /*
-     * Lookup the database in the hashtable.  Nothing to do if not there.
-     */
-    dbentry = pgstat_get_db_entry(msg->m_databaseid, false);
-
-    if (!dbentry)
-        return;
-
-    /*
-     * We simply throw away all the database's table entries by recreating a
-     * new hash table for them.
-     */
-    if (dbentry->tables != DSM_HANDLE_INVALID)
-    {
-        dshash_table *t =
-            dshash_attach(area, &dsh_tblparams, dbentry->tables, 0);
-        dshash_destroy(t);
-        dbentry->tables = DSM_HANDLE_INVALID;
-    }
-    if (dbentry->functions != DSM_HANDLE_INVALID)
-    {
-        dshash_table *t =
-            dshash_attach(area, &dsh_funcparams, dbentry->functions, 0);
-        dshash_destroy(t);
-        dbentry->functions = DSM_HANDLE_INVALID;
-    }
-
-    /*
-     * Reset database-level stats, too.  This creates empty hash tables for
-     * tables and functions.
-     */
-    reset_dbentry_counters(dbentry);
-
-    dshash_release_lock(db_stats, dbentry);
-}
-
-/* ----------
- * pgstat_recv_resetshared() -
- *
- *    Reset some shared statistics of the cluster.
- * ----------
- */
-static void
-pgstat_recv_resetsharedcounter(PgStat_MsgResetsharedcounter *msg, int len)
-{
-    if (msg->m_resettarget == RESET_BGWRITER)
-    {
-        /* Reset the global background writer statistics for the cluster. */
-        memset(&shared_globalStats, 0, sizeof(shared_globalStats));
-        shared_globalStats->stat_reset_timestamp = GetCurrentTimestamp();
-    }
-    else if (msg->m_resettarget == RESET_ARCHIVER)
-    {
-        /* Reset the archiver statistics for the cluster. */
-        memset(&shared_archiverStats, 0, sizeof(shared_archiverStats));
-        shared_archiverStats->stat_reset_timestamp = GetCurrentTimestamp();
-    }
-
-    /*
-     * Presumably the sender of this message validated the target, don't
-     * complain here if it's not valid
-     */
-}
-
-/* ----------
- * pgstat_recv_resetsinglecounter() -
- *
- *    Reset a statistics for a single object
- * ----------
- */
-static void
-pgstat_recv_resetsinglecounter(PgStat_MsgResetsinglecounter *msg, int len)
-{
-    PgStat_StatDBEntry *dbentry;
-
-    dbentry = pgstat_get_db_entry(msg->m_databaseid, false);
-
-    if (!dbentry)
-        return;
-
-    /* Set the reset timestamp for the whole database */
-    dbentry->stat_reset_timestamp = GetCurrentTimestamp();
-
-    /* Remove object if it exists, ignore it if not */
-    if (msg->m_resettype == RESET_TABLE)
-    {
-        dshash_table *t =
-            dshash_attach(area, &dsh_tblparams, dbentry->tables, 0);
-        dshash_delete_key(t, (void *) &(msg->m_objectid));
-    }
-    else if (msg->m_resettype == RESET_FUNCTION)
-    {
-        dshash_table *t =
-            dshash_attach(area, &dsh_funcparams, dbentry->functions, 0);
-        dshash_delete_key(t, (void *) &(msg->m_objectid));
-    }
-
-    dshash_release_lock(db_stats, dbentry);
-}
-
-/* ----------
- * pgstat_recv_autovac() -
- *
- *    Process an autovacuum signalling message.
- * ----------
- */
-static void
-pgstat_recv_autovac(PgStat_MsgAutovacStart *msg, int len)
-{
-    PgStat_StatDBEntry *dbentry;
-
-    /*
-     * Store the last autovacuum time in the database's hashtable entry.
-     */
-    dbentry = pgstat_get_db_entry(msg->m_databaseid, true);
-
-    dbentry->last_autovac_time = msg->m_start_time;
-
-    dshash_release_lock(db_stats, dbentry);
-}
-
-/* ----------
- * pgstat_recv_vacuum() -
- *
- *    Process a VACUUM message.
- * ----------
- */
-static void
-pgstat_recv_vacuum(PgStat_MsgVacuum *msg, int len)
-{
-    PgStat_StatDBEntry *dbentry;
-    PgStat_StatTabEntry *tabentry;
-    dshash_table *table;
-    /*
-     * Store the data in the table's hashtable entry.
-     */
-    dbentry = pgstat_get_db_entry(msg->m_databaseid, true);
-    table = dshash_attach(area, &dsh_tblparams, dbentry->tables, 0);
-    tabentry = pgstat_get_tab_entry(table, msg->m_tableoid, true);
-
-    tabentry->n_live_tuples = msg->m_live_tuples;
-    tabentry->n_dead_tuples = msg->m_dead_tuples;
-
-    if (msg->m_autovacuum)
-    {
-        tabentry->autovac_vacuum_timestamp = msg->m_vacuumtime;
-        tabentry->autovac_vacuum_count++;
+        tabentry->vacuum_timestamp = 0;
+        tabentry->vacuum_count = 0;
+        tabentry->autovac_vacuum_timestamp = 0;
+        tabentry->autovac_vacuum_count = 0;
+        tabentry->analyze_timestamp = 0;
+        tabentry->analyze_count = 0;
+        tabentry->autovac_analyze_timestamp = 0;
+        tabentry->autovac_analyze_count = 0;
     }
     else
     {
-        tabentry->vacuum_timestamp = msg->m_vacuumtime;
-        tabentry->vacuum_count++;
-    }
-    dshash_release_lock(table, tabentry);
-    dshash_detach(table);
-    dshash_release_lock(db_stats, dbentry);
-}
-
-/* ----------
- * pgstat_recv_analyze() -
- *
- *    Process an ANALYZE message.
- * ----------
- */
-static void
-pgstat_recv_analyze(PgStat_MsgAnalyze *msg, int len)
-{
-    PgStat_StatDBEntry *dbentry;
-    PgStat_StatTabEntry *tabentry;
-    dshash_table *table;
-
-    /*
-     * Store the data in the table's hashtable entry.
-     */
-    dbentry = pgstat_get_db_entry(msg->m_databaseid, true);
-
-    table = dshash_attach(area, &dsh_tblparams, dbentry->tables, 0);
-    tabentry = pgstat_get_tab_entry(table, msg->m_tableoid, true);
-
-    tabentry->n_live_tuples = msg->m_live_tuples;
-    tabentry->n_dead_tuples = msg->m_dead_tuples;
-
-    /*
-     * If commanded, reset changes_since_analyze to zero.  This forgets any
-     * changes that were committed while the ANALYZE was in progress, but we
-     * have no good way to estimate how many of those there were.
-     */
-    if (msg->m_resetcounter)
-        tabentry->changes_since_analyze = 0;
-
-    if (msg->m_autovacuum)
-    {
-        tabentry->autovac_analyze_timestamp = msg->m_analyzetime;
-        tabentry->autovac_analyze_count++;
-    }
-    else
-    {
-        tabentry->analyze_timestamp = msg->m_analyzetime;
-        tabentry->analyze_count++;
-    }
-    dshash_release_lock(table, tabentry);
-    dshash_detach(table);
-    dshash_release_lock(db_stats, dbentry);
-}
-
-
-/* ----------
- * pgstat_recv_archiver() -
- *
- *    Process a ARCHIVER message.
- * ----------
- */
-static void
-pgstat_recv_archiver(PgStat_MsgArchiver *msg, int len)
-{
-    if (msg->m_failed)
-    {
-        /* Failed archival attempt */
-        ++shared_archiverStats->failed_count;
-        memcpy(shared_archiverStats->last_failed_wal, msg->m_xlog,
-               sizeof(shared_archiverStats->last_failed_wal));
-        shared_archiverStats->last_failed_timestamp = msg->m_timestamp;
-    }
-    else
-    {
-        /* Successful archival operation */
-        ++shared_archiverStats->archived_count;
-        memcpy(shared_archiverStats->last_archived_wal, msg->m_xlog,
-               sizeof(shared_archiverStats->last_archived_wal));
-        shared_archiverStats->last_archived_timestamp = msg->m_timestamp;
-    }
-}
-
-/* ----------
- * pgstat_recv_bgwriter() -
- *
- *    Process a BGWRITER message.
- * ----------
- */
-static void
-pgstat_recv_bgwriter(PgStat_MsgBgWriter *msg, int len)
-{
-    shared_globalStats->timed_checkpoints += msg->m_timed_checkpoints;
-    shared_globalStats->requested_checkpoints += msg->m_requested_checkpoints;
-    shared_globalStats->checkpoint_write_time += msg->m_checkpoint_write_time;
-    shared_globalStats->checkpoint_sync_time += msg->m_checkpoint_sync_time;
-    shared_globalStats->buf_written_checkpoints += msg->m_buf_written_checkpoints;
-    shared_globalStats->buf_written_clean += msg->m_buf_written_clean;
-    shared_globalStats->maxwritten_clean += msg->m_maxwritten_clean;
-    shared_globalStats->buf_written_backend += msg->m_buf_written_backend;
-    shared_globalStats->buf_fsync_backend += msg->m_buf_fsync_backend;
-    shared_globalStats->buf_alloc += msg->m_buf_alloc;
-}
-
-/* ----------
- * pgstat_recv_recoveryconflict() -
- *
- *    Process a RECOVERYCONFLICT message.
- * ----------
- */
-static void
-pgstat_recv_recoveryconflict(PgStat_MsgRecoveryConflict *msg, int len)
-{
-    PgStat_StatDBEntry *dbentry;
-
-    dbentry = pgstat_get_db_entry(msg->m_databaseid, true);
-
-    switch (msg->m_reason)
-    {
-        case PROCSIG_RECOVERY_CONFLICT_DATABASE:
-
-            /*
-             * Since we drop the information about the database as soon as it
-             * replicates, there is no point in counting these conflicts.
-             */
-            break;
-        case PROCSIG_RECOVERY_CONFLICT_TABLESPACE:
-            dbentry->n_conflict_tablespace++;
-            break;
-        case PROCSIG_RECOVERY_CONFLICT_LOCK:
-            dbentry->n_conflict_lock++;
-            break;
-        case PROCSIG_RECOVERY_CONFLICT_SNAPSHOT:
-            dbentry->n_conflict_snapshot++;
-            break;
-        case PROCSIG_RECOVERY_CONFLICT_BUFFERPIN:
-            dbentry->n_conflict_bufferpin++;
-            break;
-        case PROCSIG_RECOVERY_CONFLICT_STARTUP_DEADLOCK:
-            dbentry->n_conflict_startup_deadlock++;
-            break;
-    }
-
-    dshash_release_lock(db_stats, dbentry);
-}
-
-/* ----------
- * pgstat_recv_deadlock() -
- *
- *    Process a DEADLOCK message.
- * ----------
- */
-static void
-pgstat_recv_deadlock(PgStat_MsgDeadlock *msg, int len)
-{
-    PgStat_StatDBEntry *dbentry;
-
-    dbentry = pgstat_get_db_entry(msg->m_databaseid, true);
-
-    dbentry->n_deadlocks++;
-
-    dshash_release_lock(db_stats, dbentry);
-}
-
-/* ----------
- * pgstat_recv_tempfile() -
- *
- *    Process a TEMPFILE message.
- * ----------
- */
-static void
-pgstat_recv_tempfile(PgStat_MsgTempFile *msg, int len)
-{
-    PgStat_StatDBEntry *dbentry;
-
-    dbentry = pgstat_get_db_entry(msg->m_databaseid, true);
-
-    dbentry->n_temp_bytes += msg->m_filesize;
-    dbentry->n_temp_files += 1;
-
-    dshash_release_lock(db_stats, dbentry);
-}
-
-/* ----------
- * pgstat_recv_funcstat() -
- *
- *    Count what the backend has done.
- * ----------
- */
-static void
-pgstat_recv_funcstat(PgStat_MsgFuncstat *msg, int len)
-{
-    dshash_table *t;
-    PgStat_FunctionEntry *funcmsg = &(msg->m_entry[0]);
-    PgStat_StatDBEntry *dbentry;
-    PgStat_StatFuncEntry *funcentry;
-    int            i;
-    bool        found;
-
-    dbentry = pgstat_get_db_entry(msg->m_databaseid, true);
-
-    t = dshash_attach(area, &dsh_funcparams, dbentry->functions, 0);
-    /*
-     * Process all function entries in the message.
-     */
-    for (i = 0; i < msg->m_nentries; i++, funcmsg++)
-    {
-        funcentry = (PgStat_StatFuncEntry *)
-            dshash_find_or_insert(t, (void *) &(funcmsg->f_id), &found);
-
-        if (!found)
+        /*
+         * Otherwise add the values to the existing entry.
+         */
+        tabentry->numscans += stat->t_counts.t_numscans;
+        tabentry->tuples_returned += stat->t_counts.t_tuples_returned;
+        tabentry->tuples_fetched += stat->t_counts.t_tuples_fetched;
+        tabentry->tuples_inserted += stat->t_counts.t_tuples_inserted;
+        tabentry->tuples_updated += stat->t_counts.t_tuples_updated;
+        tabentry->tuples_deleted += stat->t_counts.t_tuples_deleted;
+        tabentry->tuples_hot_updated += stat->t_counts.t_tuples_hot_updated;
+        /* If table was truncated, first reset the live/dead counters */
+        if (stat->t_counts.t_truncated)
         {
-            /*
-             * If it's a new function entry, initialize counters to the values
-             * we just got.
-             */
-            funcentry->f_numcalls = funcmsg->f_numcalls;
-            funcentry->f_total_time = funcmsg->f_total_time;
-            funcentry->f_self_time = funcmsg->f_self_time;
+            tabentry->n_live_tuples = 0;
+            tabentry->n_dead_tuples = 0;
         }
-        else
-        {
-            /*
-             * Otherwise add the values to the existing entry.
-             */
-            funcentry->f_numcalls += funcmsg->f_numcalls;
-            funcentry->f_total_time += funcmsg->f_total_time;
-            funcentry->f_self_time += funcmsg->f_self_time;
-        }
-        dshash_release_lock(t, funcentry);
+        tabentry->n_live_tuples += stat->t_counts.t_delta_live_tuples;
+        tabentry->n_dead_tuples += stat->t_counts.t_delta_dead_tuples;
+        tabentry->changes_since_analyze += stat->t_counts.t_changed_tuples;
+        tabentry->blocks_fetched += stat->t_counts.t_blocks_fetched;
+        tabentry->blocks_hit += stat->t_counts.t_blocks_hit;
     }
 
-    dshash_detach(t);
-    dshash_release_lock(db_stats, dbentry);
+    /* Clamp n_live_tuples in case of negative delta_live_tuples */
+    tabentry->n_live_tuples = Max(tabentry->n_live_tuples, 0);
+    /* Likewise for n_dead_tuples */
+    tabentry->n_dead_tuples = Max(tabentry->n_dead_tuples, 0);
+    
+    dshash_release_lock(tabhash, tabentry);
+
+    return true;
 }
 
-/* ----------
- * pgstat_recv_funcpurge() -
- *
- *    Arrange for dead function removal.
- * ----------
- */
 static void
-pgstat_recv_funcpurge(PgStat_MsgFuncpurge *msg, int len)
+pgstat_update_dbentry(PgStat_StatDBEntry *dbentry, PgStat_TableStatus *stat)
 {
-    dshash_table *t;
-    PgStat_StatDBEntry *dbentry;
-    int            i;
-
-    dbentry = pgstat_get_db_entry(msg->m_databaseid, false);
-
     /*
-     * No need to purge if we don't even know the database.
+     * Add per-table stats to the per-database entry, too.
      */
-    if (!dbentry || dbentry->functions == DSM_HANDLE_INVALID)
-        return;
-
-    t = dshash_attach(area, &dsh_funcparams, dbentry->functions, 0);
-    /*
-     * Process all function entries in the message.
-     */
-    for (i = 0; i < msg->m_nentries; i++)
-    {
-        /* Remove from hashtable if present; we don't care if it's not. */
-        dshash_delete_key(t, (void *) &(msg->m_functionid[i]));
-    }
-    dshash_detach(t);
-    dshash_release_lock(db_stats, dbentry);
+    dbentry->n_tuples_returned += stat->t_counts.t_tuples_returned;
+    dbentry->n_tuples_fetched += stat->t_counts.t_tuples_fetched;
+    dbentry->n_tuples_inserted += stat->t_counts.t_tuples_inserted;
+    dbentry->n_tuples_updated += stat->t_counts.t_tuples_updated;
+    dbentry->n_tuples_deleted += stat->t_counts.t_tuples_deleted;
+    dbentry->n_blocks_fetched += stat->t_counts.t_blocks_fetched;
+    dbentry->n_blocks_hit += stat->t_counts.t_blocks_hit;
 }
 
+
 /*
  * Convert a potentially unsafely truncated activity string (see
  * PgBackendStatus.st_activity_raw's documentation) into a correctly truncated
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 54f39ec9bb..798df0767d 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -4969,6 +4969,16 @@ SubPostmasterMain(int argc, char *argv[])
 
         PgArchiverMain(argc, argv); /* does not return */
     }
+    if (strcmp(argv[1], "--forkcol") == 0)
+    {
+        /* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+        InitProcess();
+
+        /* Attach process to shared data structures */
+        CreateSharedMemoryAndSemaphores(false, 0);
+
+        PgstatCollectorMain(argc, argv);    /* does not return */
+    }
     if (strcmp(argv[1], "--forklog") == 0)
     {
         /* Do not want to attach to shared memory */
diff --git a/src/backend/replication/logical/tablesync.c b/src/backend/replication/logical/tablesync.c
index 6e420d893c..862582da23 100644
--- a/src/backend/replication/logical/tablesync.c
+++ b/src/backend/replication/logical/tablesync.c
@@ -127,7 +127,7 @@ finish_sync_worker(void)
     if (IsTransactionState())
     {
         CommitTransactionCommand();
-        pgstat_report_stat(false);
+        pgstat_update_stat(true);
     }
 
     /* And flush all writes. */
@@ -143,6 +143,9 @@ finish_sync_worker(void)
     /* Find the main apply worker and signal it. */
     logicalrep_worker_wakeup(MyLogicalRepWorker->subid, InvalidOid);
 
+    /* clean up retained statistics */
+    pgstat_update_stat(true);
+    
     /* Stop gracefully */
     proc_exit(0);
 }
@@ -533,7 +536,7 @@ process_syncing_tables_for_apply(XLogRecPtr current_lsn)
     if (started_tx)
     {
         CommitTransactionCommand();
-        pgstat_report_stat(false);
+        pgstat_update_stat(false);
     }
 }
 
@@ -876,7 +879,7 @@ LogicalRepSyncTableStart(XLogRecPtr *origin_startpos)
                                            MyLogicalRepWorker->relstate,
                                            MyLogicalRepWorker->relstate_lsn);
                 CommitTransactionCommand();
-                pgstat_report_stat(false);
+                pgstat_update_stat(false);
 
                 /*
                  * We want to do the table data sync in a single transaction.
diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c
index e247539d7b..9719257793 100644
--- a/src/backend/replication/logical/worker.c
+++ b/src/backend/replication/logical/worker.c
@@ -491,7 +491,7 @@ apply_handle_commit(StringInfo s)
         replorigin_session_origin_timestamp = commit_data.committime;
 
         CommitTransactionCommand();
-        pgstat_report_stat(false);
+        pgstat_update_stat(false);
 
         store_flush_position(commit_data.end_lsn);
     }
@@ -1324,6 +1324,8 @@ LogicalRepApplyLoop(XLogRecPtr last_received)
             }
 
             send_feedback(last_received, requestReply, requestReply);
+
+            pgstat_update_stat(false);
         }
     }
 }
diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c
index 01eabe5706..e794a81c4c 100644
--- a/src/backend/storage/buffer/bufmgr.c
+++ b/src/backend/storage/buffer/bufmgr.c
@@ -1984,7 +1984,7 @@ BufferSync(int flags)
             if (SyncOneBuffer(buf_id, false, &wb_context) & BUF_WRITTEN)
             {
                 TRACE_POSTGRESQL_BUFFER_SYNC_WRITTEN(buf_id);
-                BgWriterStats.m_buf_written_checkpoints++;
+                BgWriterStats.buf_written_checkpoints++;
                 num_written++;
             }
         }
@@ -2092,7 +2092,7 @@ BgBufferSync(WritebackContext *wb_context)
     strategy_buf_id = StrategySyncStart(&strategy_passes, &recent_alloc);
 
     /* Report buffer alloc counts to pgstat */
-    BgWriterStats.m_buf_alloc += recent_alloc;
+    BgWriterStats.buf_alloc += recent_alloc;
 
     /*
      * If we're not running the LRU scan, just stop after doing the stats
@@ -2282,7 +2282,7 @@ BgBufferSync(WritebackContext *wb_context)
             reusable_buffers++;
             if (++num_written >= bgwriter_lru_maxpages)
             {
-                BgWriterStats.m_maxwritten_clean++;
+                BgWriterStats.maxwritten_clean++;
                 break;
             }
         }
@@ -2290,7 +2290,7 @@ BgBufferSync(WritebackContext *wb_context)
             reusable_buffers++;
     }
 
-    BgWriterStats.m_buf_written_clean += num_written;
+    BgWriterStats.buf_written_clean += num_written;
 
 #ifdef BGW_DEBUG
     elog(DEBUG1, "bgwriter: recent_alloc=%u smoothed=%.2f delta=%ld ahead=%d density=%.2f reusable_est=%d
upcoming_est=%dscanned=%d wrote=%d reusable=%d", 
diff --git a/src/backend/storage/ipc/dsm.c b/src/backend/storage/ipc/dsm.c
index 9629f22f7a..ff0ad4cce3 100644
--- a/src/backend/storage/ipc/dsm.c
+++ b/src/backend/storage/ipc/dsm.c
@@ -197,6 +197,15 @@ dsm_postmaster_startup(PGShmemHeader *shim)
     dsm_control->maxitems = maxitems;
 }
 
+/*
+ * clear dsm_init state on child start.
+ */
+void
+dsm_child_init(void)
+{
+    dsm_init_done = false;
+}
+
 /*
  * Determine whether the control segment from the previous postmaster
  * invocation still exists.  If so, remove the dynamic shared memory
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index e4c6e3d406..60296a4cef 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -3123,6 +3123,12 @@ ProcessInterrupts(void)
 
     if (ParallelMessagePending)
         HandleParallelMessages();
+
+    if (IdleStatsUpdateTimeoutPending)
+    {
+        IdleStatsUpdateTimeoutPending = false;
+        pgstat_update_stat(true);
+    }
 }
 
 
@@ -3697,6 +3703,7 @@ 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_stats_update_timeout = false;
 
     /* Initialize startup process environment if necessary. */
     if (!IsUnderPostmaster)
@@ -4137,9 +4144,17 @@ PostgresMain(int argc, char *argv[],
             }
             else
             {
-                ProcessCompletedNotifies();
-                pgstat_report_stat(false);
+                long stats_timeout;
 
+                ProcessCompletedNotifies();
+
+                stats_timeout = pgstat_update_stat(false);
+                if (stats_timeout > 0)
+                {
+                    disable_idle_stats_update_timeout = true;
+                    enable_timeout_after(IDLE_STATS_UPDATE_TIMEOUT,
+                                         stats_timeout);
+                }
                 set_ps_display("idle", false);
                 pgstat_report_activity(STATE_IDLE, NULL);
             }
@@ -4174,7 +4189,7 @@ PostgresMain(int argc, char *argv[],
         DoingCommandRead = false;
 
         /*
-         * (5) turn off the idle-in-transaction timeout
+         * (5) turn off the idle-in-transaction timeout and stats update timeout
          */
         if (disable_idle_in_transaction_timeout)
         {
@@ -4182,6 +4197,12 @@ PostgresMain(int argc, char *argv[],
             disable_idle_in_transaction_timeout = false;
         }
 
+        if (disable_idle_stats_update_timeout)
+        {
+            disable_timeout(IDLE_STATS_UPDATE_TIMEOUT, false);
+            disable_idle_stats_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 e95e347184..a5b3323f12 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -33,7 +33,7 @@
 #define UINT32_ACCESS_ONCE(var)         ((uint32)(*((volatile uint32 *)&(var))))
 
 /* Global bgwriter statistics, from bgwriter.c */
-extern PgStat_MsgBgWriter bgwriterStats;
+extern PgStat_BgWriter bgwriterStats;
 
 Datum
 pg_stat_get_numscans(PG_FUNCTION_ARGS)
@@ -1176,7 +1176,7 @@ pg_stat_get_db_xact_commit(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_xact_commit);
@@ -1192,7 +1192,7 @@ pg_stat_get_db_xact_rollback(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_xact_rollback);
@@ -1208,7 +1208,7 @@ pg_stat_get_db_blocks_fetched(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_blocks_fetched);
@@ -1224,7 +1224,7 @@ pg_stat_get_db_blocks_hit(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_blocks_hit);
@@ -1240,7 +1240,7 @@ pg_stat_get_db_tuples_returned(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_tuples_returned);
@@ -1256,7 +1256,7 @@ pg_stat_get_db_tuples_fetched(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_tuples_fetched);
@@ -1272,7 +1272,7 @@ pg_stat_get_db_tuples_inserted(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_tuples_inserted);
@@ -1288,7 +1288,7 @@ pg_stat_get_db_tuples_updated(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_tuples_updated);
@@ -1304,7 +1304,7 @@ pg_stat_get_db_tuples_deleted(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_tuples_deleted);
@@ -1319,7 +1319,7 @@ pg_stat_get_db_stat_reset_time(PG_FUNCTION_ARGS)
     TimestampTz result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = dbentry->stat_reset_timestamp;
@@ -1337,7 +1337,7 @@ pg_stat_get_db_temp_files(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = dbentry->n_temp_files;
@@ -1353,7 +1353,7 @@ pg_stat_get_db_temp_bytes(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = dbentry->n_temp_bytes;
@@ -1368,7 +1368,7 @@ pg_stat_get_db_conflict_tablespace(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_conflict_tablespace);
@@ -1383,7 +1383,7 @@ pg_stat_get_db_conflict_lock(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_conflict_lock);
@@ -1398,7 +1398,7 @@ pg_stat_get_db_conflict_snapshot(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_conflict_snapshot);
@@ -1413,7 +1413,7 @@ pg_stat_get_db_conflict_bufferpin(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_conflict_bufferpin);
@@ -1428,7 +1428,7 @@ pg_stat_get_db_conflict_startup_deadlock(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_conflict_startup_deadlock);
@@ -1443,7 +1443,7 @@ pg_stat_get_db_conflict_all(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (
@@ -1463,7 +1463,7 @@ pg_stat_get_db_deadlocks(PG_FUNCTION_ARGS)
     int64        result;
     PgStat_StatDBEntry *dbentry;
 
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = (int64) (dbentry->n_deadlocks);
@@ -1479,7 +1479,7 @@ pg_stat_get_db_blk_read_time(PG_FUNCTION_ARGS)
     PgStat_StatDBEntry *dbentry;
 
     /* convert counter from microsec to millisec for display */
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = ((double) dbentry->n_block_read_time) / 1000.0;
@@ -1495,7 +1495,7 @@ pg_stat_get_db_blk_write_time(PG_FUNCTION_ARGS)
     PgStat_StatDBEntry *dbentry;
 
     /* convert counter from microsec to millisec for display */
-    if ((dbentry = pgstat_fetch_stat_dbentry(dbid)) == NULL)
+    if ((dbentry = pgstat_fetch_stat_dbentry(dbid, false)) == NULL)
         result = 0;
     else
         result = ((double) dbentry->n_block_write_time) / 1000.0;
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 5971310aab..73fa583425 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 IdleStatsUpdateTimeoutPending = 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 4f1d2a0d28..1e4fa89135 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -72,6 +72,7 @@ static void ShutdownPostgres(int code, Datum arg);
 static void StatementTimeoutHandler(void);
 static void LockTimeoutHandler(void);
 static void IdleInTransactionSessionTimeoutHandler(void);
+static void IdleStatsUpdateTimeoutHandler(void);
 static bool ThereIsAtLeastOneRole(void);
 static void process_startup_options(Port *port, bool am_superuser);
 static void process_settings(Oid databaseid, Oid roleid);
@@ -628,6 +629,8 @@ InitPostgres(const char *in_dbname, Oid dboid, const char *username,
         RegisterTimeout(LOCK_TIMEOUT, LockTimeoutHandler);
         RegisterTimeout(IDLE_IN_TRANSACTION_SESSION_TIMEOUT,
                         IdleInTransactionSessionTimeoutHandler);
+        RegisterTimeout(IDLE_STATS_UPDATE_TIMEOUT,
+                        IdleStatsUpdateTimeoutHandler);
     }
 
     /*
@@ -1239,6 +1242,14 @@ IdleInTransactionSessionTimeoutHandler(void)
     SetLatch(MyLatch);
 }
 
+static void
+IdleStatsUpdateTimeoutHandler(void)
+{
+    IdleStatsUpdateTimeoutPending = true;
+    InterruptPending = true;
+    SetLatch(MyLatch);
+}
+
 /*
  * Returns true if at least one role is defined in this database cluster.
  */
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 433d1ed0eb..9cd31fae7b 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -81,6 +81,7 @@ 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 IdleStatsUpdateTimeoutPending;
 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 afc1927250..5db631c54c 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -39,31 +39,6 @@ typedef enum TrackFunctionsLevel
     TRACK_FUNC_ALL
 }            TrackFunctionsLevel;
 
-/* ----------
- * The types of backend -> collector messages
- * ----------
- */
-typedef enum StatMsgType
-{
-    PGSTAT_MTYPE_DUMMY,
-    PGSTAT_MTYPE_TABSTAT,
-    PGSTAT_MTYPE_TABPURGE,
-    PGSTAT_MTYPE_DROPDB,
-    PGSTAT_MTYPE_RESETCOUNTER,
-    PGSTAT_MTYPE_RESETSHAREDCOUNTER,
-    PGSTAT_MTYPE_RESETSINGLECOUNTER,
-    PGSTAT_MTYPE_AUTOVAC_START,
-    PGSTAT_MTYPE_VACUUM,
-    PGSTAT_MTYPE_ANALYZE,
-    PGSTAT_MTYPE_ARCHIVER,
-    PGSTAT_MTYPE_BGWRITER,
-    PGSTAT_MTYPE_FUNCSTAT,
-    PGSTAT_MTYPE_FUNCPURGE,
-    PGSTAT_MTYPE_RECOVERYCONFLICT,
-    PGSTAT_MTYPE_TEMPFILE,
-    PGSTAT_MTYPE_DEADLOCK
-} StatMsgType;
-
 /* ----------
  * The data type used for counters.
  * ----------
@@ -112,13 +87,6 @@ typedef struct PgStat_TableCounts
     PgStat_Counter t_blocks_hit;
 } PgStat_TableCounts;
 
-/* Possible targets for resetting cluster-wide shared values */
-typedef enum PgStat_Shared_Reset_Target
-{
-    RESET_ARCHIVER,
-    RESET_BGWRITER
-} PgStat_Shared_Reset_Target;
-
 /* Possible object types for resetting single counters */
 typedef enum PgStat_Single_Reset_Type
 {
@@ -177,242 +145,23 @@ typedef struct PgStat_TableXactStatus
 } PgStat_TableXactStatus;
 
 
-/* ------------------------------------------------------------
- * Message formats follow
- * ------------------------------------------------------------
- */
-
-
 /* ----------
- * PgStat_MsgHdr                The common message header
+ * PgStat_BgWriter            bgwriter statistics
  * ----------
  */
-typedef struct PgStat_MsgHdr
+typedef struct PgStat_BgWriter
 {
-    StatMsgType m_type;
-    int            m_size;
-} PgStat_MsgHdr;
-
-/* ----------
- * Space available in a message.  This will keep the UDP packets below 1K,
- * which should fit unfragmented into the MTU of the loopback interface.
- * (Larger values of PGSTAT_MAX_MSG_SIZE would work for that on most
- * platforms, but we're being conservative here.)
- * ----------
- */
-#define PGSTAT_MAX_MSG_SIZE 1000
-#define PGSTAT_MSG_PAYLOAD    (PGSTAT_MAX_MSG_SIZE - sizeof(PgStat_MsgHdr))
-
-
-/* ----------
- * PgStat_MsgDummy                A dummy message, ignored by the collector
- * ----------
- */
-typedef struct PgStat_MsgDummy
-{
-    PgStat_MsgHdr m_hdr;
-} PgStat_MsgDummy;
-
-/* ----------
- * PgStat_TableEntry            Per-table info in a MsgTabstat
- * ----------
- */
-typedef struct PgStat_TableEntry
-{
-    Oid            t_id;
-    PgStat_TableCounts t_counts;
-} PgStat_TableEntry;
-
-/* ----------
- * PgStat_MsgTabstat            Sent by the backend to report table
- *                                and buffer access statistics.
- * ----------
- */
-#define PGSTAT_NUM_TABENTRIES  \
-    ((PGSTAT_MSG_PAYLOAD - sizeof(Oid) - 3 * sizeof(int) - 2 * sizeof(PgStat_Counter))    \
-     / sizeof(PgStat_TableEntry))
-
-typedef struct PgStat_MsgTabstat
-{
-    PgStat_MsgHdr m_hdr;
-    Oid            m_databaseid;
-    int            m_nentries;
-    int            m_xact_commit;
-    int            m_xact_rollback;
-    PgStat_Counter m_block_read_time;    /* times in microseconds */
-    PgStat_Counter m_block_write_time;
-    PgStat_TableEntry m_entry[PGSTAT_NUM_TABENTRIES];
-} PgStat_MsgTabstat;
-
-
-/* ----------
- * PgStat_MsgTabpurge            Sent by the backend to tell the collector
- *                                about dead tables.
- * ----------
- */
-#define PGSTAT_NUM_TABPURGE  \
-    ((PGSTAT_MSG_PAYLOAD - sizeof(Oid) - sizeof(int))  \
-     / sizeof(Oid))
-
-typedef struct PgStat_MsgTabpurge
-{
-    PgStat_MsgHdr m_hdr;
-    Oid            m_databaseid;
-    int            m_nentries;
-    Oid            m_tableid[PGSTAT_NUM_TABPURGE];
-} PgStat_MsgTabpurge;
-
-
-/* ----------
- * PgStat_MsgDropdb                Sent by the backend to tell the collector
- *                                about a dropped database
- * ----------
- */
-typedef struct PgStat_MsgDropdb
-{
-    PgStat_MsgHdr m_hdr;
-    Oid            m_databaseid;
-} PgStat_MsgDropdb;
-
-
-/* ----------
- * PgStat_MsgResetcounter        Sent by the backend to tell the collector
- *                                to reset counters
- * ----------
- */
-typedef struct PgStat_MsgResetcounter
-{
-    PgStat_MsgHdr m_hdr;
-    Oid            m_databaseid;
-} PgStat_MsgResetcounter;
-
-/* ----------
- * PgStat_MsgResetsharedcounter Sent by the backend to tell the collector
- *                                to reset a shared counter
- * ----------
- */
-typedef struct PgStat_MsgResetsharedcounter
-{
-    PgStat_MsgHdr m_hdr;
-    PgStat_Shared_Reset_Target m_resettarget;
-} PgStat_MsgResetsharedcounter;
-
-/* ----------
- * PgStat_MsgResetsinglecounter Sent by the backend to tell the collector
- *                                to reset a single counter
- * ----------
- */
-typedef struct PgStat_MsgResetsinglecounter
-{
-    PgStat_MsgHdr m_hdr;
-    Oid            m_databaseid;
-    PgStat_Single_Reset_Type m_resettype;
-    Oid            m_objectid;
-} PgStat_MsgResetsinglecounter;
-
-/* ----------
- * PgStat_MsgAutovacStart        Sent by the autovacuum daemon to signal
- *                                that a database is going to be processed
- * ----------
- */
-typedef struct PgStat_MsgAutovacStart
-{
-    PgStat_MsgHdr m_hdr;
-    Oid            m_databaseid;
-    TimestampTz m_start_time;
-} PgStat_MsgAutovacStart;
-
-
-/* ----------
- * PgStat_MsgVacuum                Sent by the backend or autovacuum daemon
- *                                after VACUUM
- * ----------
- */
-typedef struct PgStat_MsgVacuum
-{
-    PgStat_MsgHdr m_hdr;
-    Oid            m_databaseid;
-    Oid            m_tableoid;
-    bool        m_autovacuum;
-    TimestampTz m_vacuumtime;
-    PgStat_Counter m_live_tuples;
-    PgStat_Counter m_dead_tuples;
-} PgStat_MsgVacuum;
-
-
-/* ----------
- * PgStat_MsgAnalyze            Sent by the backend or autovacuum daemon
- *                                after ANALYZE
- * ----------
- */
-typedef struct PgStat_MsgAnalyze
-{
-    PgStat_MsgHdr m_hdr;
-    Oid            m_databaseid;
-    Oid            m_tableoid;
-    bool        m_autovacuum;
-    bool        m_resetcounter;
-    TimestampTz m_analyzetime;
-    PgStat_Counter m_live_tuples;
-    PgStat_Counter m_dead_tuples;
-} PgStat_MsgAnalyze;
-
-
-/* ----------
- * PgStat_MsgArchiver            Sent by the archiver to update statistics.
- * ----------
- */
-typedef struct PgStat_MsgArchiver
-{
-    PgStat_MsgHdr m_hdr;
-    bool        m_failed;        /* Failed attempt */
-    char        m_xlog[MAX_XFN_CHARS + 1];
-    TimestampTz m_timestamp;
-} PgStat_MsgArchiver;
-
-/* ----------
- * PgStat_MsgBgWriter            Sent by the bgwriter to update statistics.
- * ----------
- */
-typedef struct PgStat_MsgBgWriter
-{
-    PgStat_MsgHdr m_hdr;
-
-    PgStat_Counter m_timed_checkpoints;
-    PgStat_Counter m_requested_checkpoints;
-    PgStat_Counter m_buf_written_checkpoints;
-    PgStat_Counter m_buf_written_clean;
-    PgStat_Counter m_maxwritten_clean;
-    PgStat_Counter m_buf_written_backend;
-    PgStat_Counter m_buf_fsync_backend;
-    PgStat_Counter m_buf_alloc;
-    PgStat_Counter m_checkpoint_write_time; /* times in milliseconds */
-    PgStat_Counter m_checkpoint_sync_time;
-} PgStat_MsgBgWriter;
-
-/* ----------
- * PgStat_MsgRecoveryConflict    Sent by the backend upon recovery conflict
- * ----------
- */
-typedef struct PgStat_MsgRecoveryConflict
-{
-    PgStat_MsgHdr m_hdr;
-
-    Oid            m_databaseid;
-    int            m_reason;
-} PgStat_MsgRecoveryConflict;
-
-/* ----------
- * PgStat_MsgTempFile    Sent by the backend upon creating a temp file
- * ----------
- */
-typedef struct PgStat_MsgTempFile
-{
-    PgStat_MsgHdr m_hdr;
-
-    Oid            m_databaseid;
-    size_t        m_filesize;
-} PgStat_MsgTempFile;
+    PgStat_Counter timed_checkpoints;
+    PgStat_Counter requested_checkpoints;
+    PgStat_Counter buf_written_checkpoints;
+    PgStat_Counter buf_written_clean;
+    PgStat_Counter maxwritten_clean;
+    PgStat_Counter buf_written_backend;
+    PgStat_Counter buf_fsync_backend;
+    PgStat_Counter buf_alloc;
+    PgStat_Counter checkpoint_write_time; /* times in milliseconds */
+    PgStat_Counter checkpoint_sync_time;
+} PgStat_BgWriter;
 
 /* ----------
  * PgStat_FunctionCounts    The actual per-function counts kept by a backend
@@ -453,78 +202,6 @@ typedef struct PgStat_FunctionEntry
     PgStat_Counter f_self_time;
 } PgStat_FunctionEntry;
 
-/* ----------
- * PgStat_MsgFuncstat            Sent by the backend to report function
- *                                usage statistics.
- * ----------
- */
-#define PGSTAT_NUM_FUNCENTRIES    \
-    ((PGSTAT_MSG_PAYLOAD - sizeof(Oid) - sizeof(int))  \
-     / sizeof(PgStat_FunctionEntry))
-
-typedef struct PgStat_MsgFuncstat
-{
-    PgStat_MsgHdr m_hdr;
-    Oid            m_databaseid;
-    int            m_nentries;
-    PgStat_FunctionEntry m_entry[PGSTAT_NUM_FUNCENTRIES];
-} PgStat_MsgFuncstat;
-
-/* ----------
- * PgStat_MsgFuncpurge            Sent by the backend to tell the collector
- *                                about dead functions.
- * ----------
- */
-#define PGSTAT_NUM_FUNCPURGE  \
-    ((PGSTAT_MSG_PAYLOAD - sizeof(Oid) - sizeof(int))  \
-     / sizeof(Oid))
-
-typedef struct PgStat_MsgFuncpurge
-{
-    PgStat_MsgHdr m_hdr;
-    Oid            m_databaseid;
-    int            m_nentries;
-    Oid            m_functionid[PGSTAT_NUM_FUNCPURGE];
-} PgStat_MsgFuncpurge;
-
-/* ----------
- * PgStat_MsgDeadlock            Sent by the backend to tell the collector
- *                                about a deadlock that occurred.
- * ----------
- */
-typedef struct PgStat_MsgDeadlock
-{
-    PgStat_MsgHdr m_hdr;
-    Oid            m_databaseid;
-} PgStat_MsgDeadlock;
-
-
-/* ----------
- * PgStat_Msg                    Union over all possible messages.
- * ----------
- */
-typedef union PgStat_Msg
-{
-    PgStat_MsgHdr msg_hdr;
-    PgStat_MsgDummy msg_dummy;
-    PgStat_MsgTabstat msg_tabstat;
-    PgStat_MsgTabpurge msg_tabpurge;
-    PgStat_MsgDropdb msg_dropdb;
-    PgStat_MsgResetcounter msg_resetcounter;
-    PgStat_MsgResetsharedcounter msg_resetsharedcounter;
-    PgStat_MsgResetsinglecounter msg_resetsinglecounter;
-    PgStat_MsgAutovacStart msg_autovacuum;
-    PgStat_MsgVacuum msg_vacuum;
-    PgStat_MsgAnalyze msg_analyze;
-    PgStat_MsgArchiver msg_archiver;
-    PgStat_MsgBgWriter msg_bgwriter;
-    PgStat_MsgFuncstat msg_funcstat;
-    PgStat_MsgFuncpurge msg_funcpurge;
-    PgStat_MsgRecoveryConflict msg_recoveryconflict;
-    PgStat_MsgDeadlock msg_deadlock;
-} PgStat_Msg;
-
-
 /* ------------------------------------------------------------
  * Statistic collector data structures follow
  *
@@ -1111,7 +788,7 @@ extern char *pgstat_stat_filename;
 /*
  * BgWriter statistics counters are updated directly by bgwriter and bufmgr
  */
-extern PgStat_MsgBgWriter BgWriterStats;
+extern PgStat_BgWriter BgWriterStats;
 
 /*
  * Updated by pgstat_count_buffer_*_time macros
@@ -1123,9 +800,6 @@ extern PgStat_Counter pgStatBlockWriteTime;
  * Functions called from postmaster
  * ----------
  */
-extern Size BackendStatusShmemSize(void);
-extern void CreateSharedBackendStatus(void);
-
 extern void pgstat_init(void);
 extern int    pgstat_start(void);
 extern void pgstat_reset_all(void);
@@ -1135,17 +809,14 @@ extern void allow_immediate_pgstat_restart(void);
  * Functions called from backends
  * ----------
  */
-extern void pgstat_ping(void);
-
-extern void pgstat_report_stat(bool force);
+extern long pgstat_update_stat(bool force);
 extern void pgstat_vacuum_stat(void);
 extern void pgstat_drop_database(Oid databaseid);
 
-extern void pgstat_clear_snapshot(void);
 extern void pgstat_reset_counters(void);
-extern void pgstat_reset_shared_counters(const char *);
-extern void pgstat_reset_single_counter(Oid objectid, PgStat_Single_Reset_Type type);
-
+extern void pgstat_reset_shared_counters(const char *target);
+extern void pgstat_reset_single_counter(Oid objectid,
+                                        PgStat_Single_Reset_Type type);
 extern void pgstat_report_autovac(Oid dboid);
 extern void pgstat_report_vacuum(Oid tableoid, bool shared,
                      PgStat_Counter livetuples, PgStat_Counter deadtuples);
@@ -1156,6 +827,8 @@ extern void pgstat_report_analyze(Relation rel,
 extern void pgstat_report_recovery_conflict(int reason);
 extern void pgstat_report_deadlock(void);
 
+extern void pgstat_clear_snapshot(void);
+
 extern void pgstat_initialize(void);
 extern void pgstat_bestart(void);
 
@@ -1305,15 +978,15 @@ extern void pgstat_twophase_postcommit(TransactionId xid, uint16 info,
 extern void pgstat_twophase_postabort(TransactionId xid, uint16 info,
                           void *recdata, uint32 len);
 
-extern void pgstat_send_archiver(const char *xlog, bool failed);
-extern void pgstat_send_bgwriter(void);
+extern void pgstat_update_archiver(const char *xlog, bool failed);
+extern void pgstat_update_bgwriter(void);
 
 /* ----------
  * Support functions for the SQL-callable functions to
  * generate the pgstat* views.
  * ----------
  */
-extern PgStat_StatDBEntry *pgstat_fetch_stat_dbentry(Oid dbid);
+extern PgStat_StatDBEntry *pgstat_fetch_stat_dbentry(Oid relid, bool oneshot);
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
 extern PgBackendStatus *pgstat_fetch_stat_beentry(int beid);
 extern LocalPgBackendStatus *pgstat_fetch_stat_local_beentry(int beid);
@@ -1322,9 +995,13 @@ extern int    pgstat_fetch_stat_numbackends(void);
 extern PgStat_ArchiverStats *pgstat_fetch_stat_archiver(void);
 extern PgStat_GlobalStats *pgstat_fetch_global(void);
 
-/* Main loop */
-extern void PgstatCollectorMain(void) pg_attribute_noreturn();
+/* File input/output functions  */
+extern void pgstat_read_statsfiles(void);
+extern void pgstat_write_statsfiles(void);
 
+/* For shared memory allocation/initialize */
+extern Size BackendStatusShmemSize(void);
+extern void CreateSharedBackendStatus(void);
 extern Size StatsShmemSize(void);
 extern void StatsShmemInit(void);
 
diff --git a/src/include/storage/dsm.h b/src/include/storage/dsm.h
index 169de946f7..3c3da7ace6 100644
--- a/src/include/storage/dsm.h
+++ b/src/include/storage/dsm.h
@@ -26,6 +26,7 @@ typedef struct dsm_segment dsm_segment;
 struct PGShmemHeader;            /* avoid including pg_shmem.h */
 extern void dsm_cleanup_using_control_segment(dsm_handle old_control_handle);
 extern void dsm_postmaster_startup(struct PGShmemHeader *);
+extern void dsm_child_init(void);
 extern void dsm_backend_shutdown(void);
 extern void dsm_detach_all(void);
 
diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h
index dcc7307c16..b8a56645b6 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_STATS_UPDATE_TIMEOUT,
     /* First user-definable timeout reason */
     USER_TIMEOUT,
     /* Maximum number of timeout reasons */
diff --git a/src/test/modules/worker_spi/worker_spi.c b/src/test/modules/worker_spi/worker_spi.c
index 0d705a3f2e..da488ebfd4 100644
--- a/src/test/modules/worker_spi/worker_spi.c
+++ b/src/test/modules/worker_spi/worker_spi.c
@@ -295,7 +295,7 @@ worker_spi_main(Datum main_arg)
         SPI_finish();
         PopActiveSnapshot();
         CommitTransactionCommand();
-        pgstat_report_stat(false);
+        pgstat_update_stat(false);
         pgstat_report_activity(STATE_IDLE, NULL);
     }
 
-- 
2.16.3

From 1738edcfed77f5cb709f3c200f1db2d2837d853d Mon Sep 17 00:00:00 2001
From: Kyotaro Horiguchi <horiguchi.kyotaro@lab.ntt.co.jp>
Date: Wed, 3 Oct 2018 17:10:46 +0900
Subject: [PATCH 08/10] Allow delettion while dshash sequential scan

The previous version of dshash_seq_scan is not allow deletion while
scanning. This patch allows that in the same way with dynahash.
---
 src/backend/lib/dshash.c | 89 +++++++++++++++++++++++++++++++++++-------------
 src/include/lib/dshash.h |  4 ++-
 2 files changed, 68 insertions(+), 25 deletions(-)

diff --git a/src/backend/lib/dshash.c b/src/backend/lib/dshash.c
index 7584931515..e71d189ab6 100644
--- a/src/backend/lib/dshash.c
+++ b/src/backend/lib/dshash.c
@@ -112,6 +112,7 @@ struct dshash_table
     size_t        size_log2;        /* log2(number of buckets) */
     bool        find_locked;    /* Is any partition lock held by 'find'? */
     bool        find_exclusively_locked;    /* ... exclusively? */
+    bool        seqscan_running;/* now under sequential scan */
 };
 
 /* Given a pointer to an item, find the entry (user data) it holds. */
@@ -153,6 +154,10 @@ struct dshash_table
 #define BUCKET_INDEX_FOR_PARTITION(partition, size_log2)    \
     ((partition) << NUM_SPLITS(size_log2))
 
+/* Choose partition based on bucket index. */
+#define PARTITION_FOR_BUCKET_INDEX(bucket_idx, size_log2)                \
+    ((bucket_idx) >> NUM_SPLITS(size_log2))
+
 /* The head of the active bucket for a given hash value (lvalue). */
 #define BUCKET_FOR_HASH(hash_table, hash)                                \
     (hash_table->buckets[                                                \
@@ -228,6 +233,7 @@ dshash_create(dsa_area *area, const dshash_parameters *params, void *arg)
 
     hash_table->find_locked = false;
     hash_table->find_exclusively_locked = false;
+    hash_table->seqscan_running = false;
 
     /*
      * Set up the initial array of buckets.  Our initial size is the same as
@@ -279,6 +285,7 @@ dshash_attach(dsa_area *area, const dshash_parameters *params,
     hash_table->control = dsa_get_address(area, control);
     hash_table->find_locked = false;
     hash_table->find_exclusively_locked = false;
+    hash_table->seqscan_running = false;
     Assert(hash_table->control->magic == DSHASH_MAGIC);
 
     /*
@@ -599,9 +606,14 @@ dshash_delete_entry(dshash_table *hash_table, void *entry)
                                 LW_EXCLUSIVE));
 
     delete_item(hash_table, item);
-    hash_table->find_locked = false;
-    hash_table->find_exclusively_locked = false;
-    LWLockRelease(PARTITION_LOCK(hash_table, partition));
+
+    /* We need to keep partition lock while sequential scan */
+    if (!hash_table->seqscan_running)
+    {
+        hash_table->find_locked = false;
+        hash_table->find_exclusively_locked = false;
+        LWLockRelease(PARTITION_LOCK(hash_table, partition));
+    }
 }
 
 /*
@@ -618,6 +630,8 @@ dshash_release_lock(dshash_table *hash_table, void *entry)
     Assert(LWLockHeldByMeInMode(PARTITION_LOCK(hash_table, partition_index),
                                 hash_table->find_exclusively_locked
                                 ? LW_EXCLUSIVE : LW_SHARED));
+    /* don't allow during sequential scan */
+    Assert(!hash_table->seqscan_running);
 
     hash_table->find_locked = false;
     hash_table->find_exclusively_locked = false;
@@ -664,14 +678,20 @@ dshash_memhash(const void *v, size_t size, void *arg)
  */
 void
 dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
-                bool consistent)
+                bool consistent, bool exclusive)
 {
+    /* allowed at most one scan at once */
+    Assert(!hash_table->seqscan_running);
+
     status->hash_table = hash_table;
     status->curbucket = 0;
     status->nbuckets = ((size_t) 1) << hash_table->control->size_log2;
     status->curitem = NULL;
+    status->pnextitem = InvalidDsaPointer;
     status->curpartition = -1;
     status->consistent = consistent;
+    status->exclusive = exclusive;
+    hash_table->seqscan_running = true;
 
     /*
      * Protect all partitions from modification if the caller wants a
@@ -685,7 +705,8 @@ dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
         {
             Assert(!LWLockHeldByMe(PARTITION_LOCK(hash_table, i)));
 
-            LWLockAcquire(PARTITION_LOCK(hash_table, i), LW_SHARED);
+            LWLockAcquire(PARTITION_LOCK(hash_table, i),
+                          exclusive ? LW_EXCLUSIVE : LW_SHARED);
         }
     }
     ensure_valid_bucket_pointers(hash_table);
@@ -696,17 +717,29 @@ dshash_seq_next(dshash_seq_status *status)
 {
     dsa_pointer next_item_pointer;
 
+    Assert(status->hash_table->seqscan_running);
     if (status->curitem == NULL)
     {
+        int partition;
+
         Assert (status->curbucket == 0);
         Assert(!status->hash_table->find_locked);
 
         /* first shot. grab the first item. */
+        if (!status->consistent)
+        {
+            partition =
+                PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+                                           status->hash_table->size_log2);
+            LWLockAcquire(PARTITION_LOCK(status->hash_table, partition),
+                          status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
+            status->curpartition = partition;
+        }
+        
         next_item_pointer = status->hash_table->buckets[status->curbucket];
-        status->hash_table->find_locked = true;
     }
     else
-        next_item_pointer = status->curitem->next;
+        next_item_pointer = status->pnextitem;
 
     /* Move to the next bucket if we finished the current bucket */
     while (!DsaPointerIsValid(next_item_pointer))
@@ -717,42 +750,50 @@ dshash_seq_next(dshash_seq_status *status)
             dshash_seq_term(status);
             return NULL;
         }
-        Assert(status->hash_table->find_locked);
 
-        next_item_pointer = status->hash_table->buckets[status->curbucket];
-
-        /*
-         * we need a lock on the scanning partition even if the caller don't
-         * requested a consistent snapshot.
-         */
-        if (!status->consistent && DsaPointerIsValid(next_item_pointer))
+        /* Also move parititon lock if needed */
+        if (!status->consistent)
         {
-            dshash_table_item  *item = dsa_get_address(status->hash_table->area,
-                                                       next_item_pointer);
-            int next_partition = PARTITION_FOR_HASH(item->hash);
+            int next_partition =
+                PARTITION_FOR_BUCKET_INDEX(status->curbucket,
+                                           status->hash_table->size_log2);
+
+            /* Move lock along with partition for the bucket */
             if (status->curpartition != next_partition)
             {
-                if (status->curpartition >= 0)
-                    LWLockRelease(PARTITION_LOCK(status->hash_table,
-                                                 status->curpartition));
+                LWLockRelease(PARTITION_LOCK(status->hash_table,
+                                             status->curpartition));
                 LWLockAcquire(PARTITION_LOCK(status->hash_table,
                                              next_partition),
-                              LW_SHARED);
+                              status->exclusive ? LW_EXCLUSIVE : LW_SHARED);
                 status->curpartition = next_partition;
             }
         }
+
+        next_item_pointer = status->hash_table->buckets[status->curbucket];
     }
 
     status->curitem =
         dsa_get_address(status->hash_table->area, next_item_pointer);
+    status->hash_table->find_locked = true;
+    status->hash_table->find_exclusively_locked = status->exclusive;
+
+    /*
+     * This item can be deleted by the caller. Store the next item for the
+     * next iteration for the occasion.
+     */
+    status->pnextitem = status->curitem->next;
+
     return ENTRY_FROM_ITEM(status->curitem);
 }
 
 void
 dshash_seq_term(dshash_seq_status *status)
 {
-    Assert(status->hash_table->find_locked);
+    Assert(status->hash_table->seqscan_running);
     status->hash_table->find_locked = false;
+    status->hash_table->find_exclusively_locked = false;
+    status->hash_table->seqscan_running = false;
 
     if (status->consistent)
     {
@@ -773,7 +814,7 @@ dshash_get_num_entries(dshash_table *hash_table)
     void *p;
     int n = 0;
 
-    dshash_seq_init(&s, hash_table, false);
+    dshash_seq_init(&s, hash_table, false, false);
     while ((p = dshash_seq_next(&s)) != NULL)
         n++;
 
diff --git a/src/include/lib/dshash.h b/src/include/lib/dshash.h
index b207585eeb..1b3e01000b 100644
--- a/src/include/lib/dshash.h
+++ b/src/include/lib/dshash.h
@@ -71,8 +71,10 @@ typedef struct dshash_seq_status
     int                    curbucket;
     int                    nbuckets;
     dshash_table_item  *curitem;
+    dsa_pointer            pnextitem;
     int                    curpartition;
     bool                consistent;
+    bool                exclusive;
 } dshash_seq_status;
 
 /* Creating, sharing and destroying from hash tables. */
@@ -101,7 +103,7 @@ extern void dshash_release_lock(dshash_table *hash_table, void *entry);
 
 /* seq scan support */
 extern void dshash_seq_init(dshash_seq_status *status, dshash_table *hash_table,
-                            bool exclusive);
+                            bool consistent, bool exclusive);
 extern void *dshash_seq_next(dshash_seq_status *status);
 extern void dshash_seq_term(dshash_seq_status *status);
 extern int dshash_get_num_entries(dshash_table *hash_table);
-- 
2.16.3


В списке pgsql-hackers по дате отправления:

Предыдущее
От: "Yotsunaga, Naoki"
Дата:
Сообщение: RE: [Proposal] Add accumulated statistics for wait event
Следующее
От: Konstantin Knizhnik
Дата:
Сообщение: Re: out-of-order XID insertion in KnownAssignedXids