Fix performance regression with flush of pending fixed-numbered stats

michaelpq · michaelpq · commit 13eb6bb76d5d · 2025-07-28T08:15:16.000+09:00
The callback added in fc415ed used to check if there is any pending data to flush for fixed-numbered statistics, done by looping across all the builtin and custom stats kinds with a call to have_fixed_pending_cb, is proving to able to show in workloads that do not report any stats (read-only, no function calls, no WAL, no IO, etc). The code used in v17 was cheaper than that what HEAD has introduced, relying on three boolean checks for WAL, SLRU and IO stats. This commit switches the code to use a more efficient approach than fc415ed, with a single boolean flag that can be switched to "true" by any fixed-numbered stats kinds to force pgstat_report_stat() to go through one round of reports. The flag is reset by pgstat_report_stat() once a full round of reports is done. The flag being false means that fixed-numbered stats kinds saw no activity, and that there is no pending data to flush. ac000fc took one step in improving the performance by reducing the number of stats kinds that the backend can hold. This commit takes a more drastic step by bringing back the code efficiency to what it was before v18 with a cheap check at the beginning of pgstat_report_stat() for its fast-exit path. The callback have_static_pending_cb is removed as an effect of all that. Reported-by: Andres Freund <andres@anarazel.de> Reviewed-by: Bertrand Drouvot <bertranddrouvot.pg@gmail.com> Discussion: https://postgr.es/m/eb224uegsga2hgq7dfq3ps5cduhpqej7ir2hjxzzozjthrekx5@dysei6buqthe Backpatch-through: 18
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
@@ -96,6 +96,7 @@
 #include "utils/guc_hooks.h"
 #include "utils/guc_tables.h"
 #include "utils/injection_point.h"
+#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
 #include "utils/relmapper.h"
 #include "utils/snapmgr.h"
@@ -1092,6 +1093,9 @@ XLogInsertRecord(XLogRecData *rdata,
 		pgWalUsage.wal_bytes += rechdr->xl_tot_len;
 		pgWalUsage.wal_records++;
 		pgWalUsage.wal_fpi += num_fpi;
+
+		/* Required for the flush of pending stats WAL data */
+		pgstat_report_fixed = true;
 	}
 
 	return EndPos;
@@ -2109,6 +2113,12 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic)
 					LWLockRelease(WALWriteLock);
 					pgWalUsage.wal_buffers_full++;
 					TRACE_POSTGRESQL_WAL_BUFFER_WRITE_DIRTY_DONE();
+
+					/*
+					 * Required for the flush of pending stats WAL data, per
+					 * update of pgWalUsage.
+					 */
+					pgstat_report_fixed = true;
 				}
 			}
 		}
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
@@ -212,6 +212,11 @@ int			pgstat_fetch_consistency = PGSTAT_FETCH_CONSISTENCY_CACHE;
 
 PgStat_LocalState pgStatLocal;
 
+/*
+ * Track pending reports for fixed-numbered stats, used by
+ * pgstat_report_stat().
+ */
+bool		pgstat_report_fixed = false;
 
 /* ----------
  * Local data
@@ -370,7 +375,6 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_off = offsetof(PgStatShared_Backend, stats),
 		.shared_data_len = sizeof(((PgStatShared_Backend *) 0)->stats),
 
-		.have_static_pending_cb = pgstat_backend_have_pending_cb,
 		.flush_static_cb = pgstat_backend_flush_cb,
 		.reset_timestamp_cb = pgstat_backend_reset_timestamp_cb,
 	},
@@ -437,7 +441,6 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_IO *) 0)->stats),
 
 		.flush_static_cb = pgstat_io_flush_cb,
-		.have_static_pending_cb = pgstat_io_have_pending_cb,
 		.init_shmem_cb = pgstat_io_init_shmem_cb,
 		.reset_all_cb = pgstat_io_reset_all_cb,
 		.snapshot_cb = pgstat_io_snapshot_cb,
@@ -455,7 +458,6 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 		.shared_data_len = sizeof(((PgStatShared_SLRU *) 0)->stats),
 
 		.flush_static_cb = pgstat_slru_flush_cb,
-		.have_static_pending_cb = pgstat_slru_have_pending_cb,
 		.init_shmem_cb = pgstat_slru_init_shmem_cb,
 		.reset_all_cb = pgstat_slru_reset_all_cb,
 		.snapshot_cb = pgstat_slru_snapshot_cb,
@@ -474,7 +476,6 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.init_backend_cb = pgstat_wal_init_backend_cb,
 		.flush_static_cb = pgstat_wal_flush_cb,
-		.have_static_pending_cb = pgstat_wal_have_pending_cb,
 		.init_shmem_cb = pgstat_wal_init_shmem_cb,
 		.reset_all_cb = pgstat_wal_reset_all_cb,
 		.snapshot_cb = pgstat_wal_snapshot_cb,
@@ -708,29 +709,10 @@ pgstat_report_stat(bool force)
 	}
 
 	/* Don't expend a clock check if nothing to do */
-	if (dlist_is_empty(&pgStatPending))
+	if (dlist_is_empty(&pgStatPending) &&
+		!pgstat_report_fixed)
 	{
-		bool		do_flush = false;
-
-		/* Check for pending stats */
-		for (PgStat_Kind kind = PGSTAT_KIND_MIN; kind <= PGSTAT_KIND_MAX; kind++)
-		{
-			const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
-
-			if (!kind_info)
-				continue;
-			if (!kind_info->have_static_pending_cb)
-				continue;
-
-			if (kind_info->have_static_pending_cb())
-			{
-				do_flush = true;
-				break;
-			}
-		}
-
-		if (!do_flush)
-			return 0;
+		return 0;
 	}
 
 	/*
@@ -784,16 +766,19 @@ pgstat_report_stat(bool force)
 	partial_flush |= pgstat_flush_pending_entries(nowait);
 
 	/* flush of other stats kinds */
-	for (PgStat_Kind kind = PGSTAT_KIND_MIN; kind <= PGSTAT_KIND_MAX; kind++)
+	if (pgstat_report_fixed)
 	{
-		const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
+		for (PgStat_Kind kind = PGSTAT_KIND_MIN; kind <= PGSTAT_KIND_MAX; kind++)
+		{
+			const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
 
-		if (!kind_info)
-			continue;
-		if (!kind_info->flush_static_cb)
-			continue;
+			if (!kind_info)
+				continue;
+			if (!kind_info->flush_static_cb)
+				continue;
 
-		partial_flush |= kind_info->flush_static_cb(nowait);
+			partial_flush |= kind_info->flush_static_cb(nowait);
+		}
 	}
 
 	last_flush = now;
@@ -815,6 +800,7 @@ pgstat_report_stat(bool force)
 	}
 
 	pending_since = 0;
+	pgstat_report_fixed = false;
 
 	return 0;
 }
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
@@ -66,6 +66,7 @@ pgstat_count_backend_io_op_time(IOObject io_object, IOContext io_context,
 				   io_time);
 
 	backend_has_iostats = true;
+	pgstat_report_fixed = true;
 }
 
 void
@@ -81,6 +82,7 @@ pgstat_count_backend_io_op(IOObject io_object, IOContext io_context,
 	PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
 
 	backend_has_iostats = true;
+	pgstat_report_fixed = true;
 }
 
 /*
@@ -301,18 +303,6 @@ pgstat_flush_backend(bool nowait, bits32 flags)
 	return false;
 }
 
-/*
- * Check if there are any backend stats waiting for flush.
- */
-bool
-pgstat_backend_have_pending_cb(void)
-{
-	if (!pgstat_tracks_backend_bktype(MyBackendType))
-		return false;
-
-	return (backend_has_iostats || pgstat_backend_wal_have_pending());
-}
-
 /*
  * Callback to flush out locally pending backend statistics.
  *
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
@@ -80,6 +80,7 @@ pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op,
 	pgstat_count_backend_io_op(io_object, io_context, io_op, cnt, bytes);
 
 	have_iostats = true;
+	pgstat_report_fixed = true;
 }
 
 /*
@@ -167,15 +168,6 @@ pgstat_fetch_stat_io(void)
 	return &pgStatLocal.snapshot.io;
 }
 
-/*
- * Check if there any IO stats waiting for flush.
- */
-bool
-pgstat_io_have_pending_cb(void)
-{
-	return have_iostats;
-}
-
 /*
  * Simpler wrapper of pgstat_io_flush_cb()
  */
diff --git a/src/backend/utils/activity/pgstat_slru.c b/src/backend/utils/activity/pgstat_slru.c
@@ -143,15 +143,6 @@ pgstat_get_slru_index(const char *name)
 	return (SLRU_NUM_ELEMENTS - 1);
 }
 
-/*
- * Check if there are any SLRU stats entries waiting for flush.
- */
-bool
-pgstat_slru_have_pending_cb(void)
-{
-	return have_slrustats;
-}
-
 /*
  * Flush out locally pending SLRU stats entries
  *
@@ -247,6 +238,7 @@ get_slru_entry(int slru_idx)
 	Assert((slru_idx >= 0) && (slru_idx < SLRU_NUM_ELEMENTS));
 
 	have_slrustats = true;
+	pgstat_report_fixed = true;
 
 	return &pending_SLRUStats[slru_idx];
 }
diff --git a/src/backend/utils/activity/pgstat_wal.c b/src/backend/utils/activity/pgstat_wal.c
@@ -71,6 +71,15 @@ pgstat_fetch_stat_wal(void)
 	return &pgStatLocal.snapshot.wal;
 }
 
+/*
+ * To determine whether WAL usage happened.
+ */
+static inline bool
+pgstat_wal_have_pending(void)
+{
+	return pgWalUsage.wal_records != prevWalUsage.wal_records;
+}
+
 /*
  * Calculate how much WAL usage counters have increased by subtracting the
  * previous counters from the current ones.
@@ -92,7 +101,7 @@ pgstat_wal_flush_cb(bool nowait)
 	 * This function can be called even if nothing at all has happened. Avoid
 	 * taking lock for nothing in that case.
 	 */
-	if (!pgstat_wal_have_pending_cb())
+	if (!pgstat_wal_have_pending())
 		return false;
 
 	/*
@@ -136,15 +145,6 @@ pgstat_wal_init_backend_cb(void)
 	prevWalUsage = pgWalUsage;
 }
 
-/*
- * To determine whether WAL usage happened.
- */
-bool
-pgstat_wal_have_pending_cb(void)
-{
-	return pgWalUsage.wal_records != prevWalUsage.wal_records;
-}
-
 void
 pgstat_wal_init_shmem_cb(void *stats)
 {
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
@@ -295,18 +295,11 @@ typedef struct PgStat_KindInfo
 	 *
 	 * Returns true if some of the stats could not be flushed, due to lock
 	 * contention for example. Optional.
-	 */
-	bool		(*flush_static_cb) (bool nowait);
-
-	/*
-	 * For fixed-numbered or variable-numbered statistics: Check for pending
-	 * stats in need of flush with flush_static_cb, when these do not use
-	 * PgStat_EntryRef->pending.
 	 *
-	 * Returns true if there are any stats pending for flush, triggering
-	 * flush_static_cb. Optional.
+	 * "pgstat_report_fixed" needs to be set to trigger the flush of pending
+	 * stats.
 	 */
-	bool		(*have_static_pending_cb) (void);
+	bool		(*flush_static_cb) (bool nowait);
 
 	/*
 	 * For fixed-numbered statistics: Reset All.
@@ -627,7 +620,6 @@ extern void pgstat_archiver_snapshot_cb(void);
 
 extern bool pgstat_flush_backend(bool nowait, bits32 flags);
 extern bool pgstat_backend_flush_cb(bool nowait);
-extern bool pgstat_backend_have_pending_cb(void);
 extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header,
 											  TimestampTz ts);
 
@@ -676,7 +668,6 @@ extern bool pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 
 extern void pgstat_flush_io(bool nowait);
 
-extern bool pgstat_io_have_pending_cb(void);
 extern bool pgstat_io_flush_cb(bool nowait);
 extern void pgstat_io_init_shmem_cb(void *stats);
 extern void pgstat_io_reset_all_cb(TimestampTz ts);
@@ -738,7 +729,6 @@ extern PgStatShared_Common *pgstat_init_entry(PgStat_Kind kind,
  * Functions in pgstat_slru.c
  */
 
-extern bool pgstat_slru_have_pending_cb(void);
 extern bool pgstat_slru_flush_cb(bool nowait);
 extern void pgstat_slru_init_shmem_cb(void *stats);
 extern void pgstat_slru_reset_all_cb(TimestampTz ts);
@@ -750,7 +740,6 @@ extern void pgstat_slru_snapshot_cb(void);
  */
 
 extern void pgstat_wal_init_backend_cb(void);
-extern bool pgstat_wal_have_pending_cb(void);
 extern bool pgstat_wal_flush_cb(bool nowait);
 extern void pgstat_wal_init_shmem_cb(void *stats);
 extern void pgstat_wal_reset_all_cb(TimestampTz ts);
@@ -778,8 +767,23 @@ extern void pgstat_create_transactional(PgStat_Kind kind, Oid dboid, uint64 obji
  * Variables in pgstat.c
  */
 
-extern PGDLLIMPORT PgStat_LocalState pgStatLocal;
+/*
+ * Track if *any* pending fixed-numbered statistics should be flushed to
+ * shared memory.
+ *
+ * This flag can be switched to true by fixed-numbered statistics to let
+ * pgstat_report_stat() know if it needs to go through one round of
+ * reports, calling flush_static_cb for each fixed-numbered statistics
+ * kind.  When this flag is not set, pgstat_report_stat() is able to do
+ * a fast exit, knowing that there are no pending fixed-numbered statistics.
+ *
+ * Statistics callbacks should never reset this flag; pgstat_report_stat()
+ * is in charge of doing that.
+ */
+extern PGDLLIMPORT bool pgstat_report_fixed;
 
+/* Backend-local stats state */
+extern PGDLLIMPORT PgStat_LocalState pgStatLocal;
 
 /*
  * Implementation of inline functions declared above.
