agora inbox for [email protected]  
help / color / mirror / Atom feed
[PATCH] Implementation of Index Skip Scan (see Loose Index Scan in the wiki [1]) on top of IndexOnlyScan. To make it suitable for both situations when there are small number of distinct values and significant amount of distinct values the following approach is taken - instead of searching from the root for every value we're searching for then first on the current page, and then if not found continue searching from the root.
12+ messages / 2 participants
[nested] [flat]

* [PATCH] Implementation of Index Skip Scan (see Loose Index Scan in the wiki [1]) on top of IndexOnlyScan. To make it suitable for both situations when there are small number of distinct values and significant amount of distinct values the following approach is taken - instead of searching from the root for every value we're searching for then first on the current page, and then if not found continue searching from the root.
@ 2019-06-13 13:04 jesperpedersen <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: jesperpedersen @ 2019-06-13 13:04 UTC (permalink / raw)

Original patch and design were proposed by Thomas Munro [2], revived and
improved by Dmitry Dolgov and Jesper Pedersen.

[1] https://wiki.postgresql.org/wiki/Loose_indexscan
[2] https://www.postgresql.org/message-id/flat/CADLWmXXbTSBxP-MzJuPAYSsL_2f0iPm5VWPbCvDbVvfX93FKkw%40mai...
---
 contrib/bloom/blutils.c                       |   1 +
 doc/src/sgml/config.sgml                      |  16 ++
 doc/src/sgml/indexam.sgml                     |  10 +
 doc/src/sgml/indices.sgml                     |  24 ++
 src/backend/access/brin/brin.c                |   1 +
 src/backend/access/gin/ginutil.c              |   1 +
 src/backend/access/gist/gist.c                |   1 +
 src/backend/access/hash/hash.c                |   1 +
 src/backend/access/index/indexam.c            |  16 ++
 src/backend/access/nbtree/nbtree.c            |  12 +
 src/backend/access/nbtree/nbtsearch.c         | 224 +++++++++++++++++-
 src/backend/access/spgist/spgutils.c          |   1 +
 src/backend/commands/explain.c                |  12 +
 src/backend/executor/nodeIndexonlyscan.c      |  22 ++
 src/backend/nodes/copyfuncs.c                 |   1 +
 src/backend/nodes/outfuncs.c                  |   2 +
 src/backend/nodes/readfuncs.c                 |   1 +
 src/backend/optimizer/path/costsize.c         |   1 +
 src/backend/optimizer/path/pathkeys.c         |  84 ++++++-
 src/backend/optimizer/plan/createplan.c       |  10 +-
 src/backend/optimizer/plan/planagg.c          |   1 +
 src/backend/optimizer/plan/planner.c          |  67 +++++-
 src/backend/optimizer/util/pathnode.c         |  40 ++++
 src/backend/optimizer/util/plancat.c          |   1 +
 src/backend/utils/misc/guc.c                  |   9 +
 src/backend/utils/misc/postgresql.conf.sample |   1 +
 src/include/access/amapi.h                    |   5 +
 src/include/access/genam.h                    |   1 +
 src/include/access/nbtree.h                   |   5 +
 src/include/nodes/execnodes.h                 |   4 +
 src/include/nodes/pathnodes.h                 |   8 +
 src/include/nodes/plannodes.h                 |   1 +
 src/include/optimizer/cost.h                  |   1 +
 src/include/optimizer/pathnode.h              |   5 +
 src/include/optimizer/paths.h                 |   4 +
 src/test/regress/expected/create_index.out    |   1 +
 src/test/regress/expected/select_distinct.out | 176 ++++++++++++++
 src/test/regress/expected/sysviews.out        |   3 +-
 src/test/regress/sql/create_index.sql         |   2 +
 src/test/regress/sql/select_distinct.sql      |  55 +++++
 40 files changed, 812 insertions(+), 19 deletions(-)

diff --git a/contrib/bloom/blutils.c b/contrib/bloom/blutils.c
index ee3bd56274..a88b730f2e 100644
--- a/contrib/bloom/blutils.c
+++ b/contrib/bloom/blutils.c
@@ -129,6 +129,7 @@ blhandler(PG_FUNCTION_ARGS)
 	amroutine->ambulkdelete = blbulkdelete;
 	amroutine->amvacuumcleanup = blvacuumcleanup;
 	amroutine->amcanreturn = NULL;
+	amroutine->amskip = NULL;
 	amroutine->amcostestimate = blcostestimate;
 	amroutine->amoptions = bloptions;
 	amroutine->amproperty = NULL;
diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 84341a30e5..a1c8a1ea27 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -4400,6 +4400,22 @@ ANY <replaceable class="parameter">num_sync</replaceable> ( <replaceable class="
       </listitem>
      </varlistentry>
 
+     <varlistentry id="guc-enable-indexskipscan" xreflabel="enable_indexskipscan">
+      <term><varname>enable_indexskipscan</varname> (<type>boolean</type>)
+      <indexterm>
+       <primary><varname>enable_indexskipscan</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        Enables or disables the query planner's use of index-skip-scan plan
+        types (see <xref linkend="indexes-index-skip-scans"/>). This parameter requires
+        that <varname>enable_indexonlyscan</varname> is <literal>on</literal>.
+        The default is <literal>on</literal>.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="guc-enable-material" xreflabel="enable_material">
       <term><varname>enable_material</varname> (<type>boolean</type>)
       <indexterm>
diff --git a/doc/src/sgml/indexam.sgml b/doc/src/sgml/indexam.sgml
index dd54c68802..c2eb296306 100644
--- a/doc/src/sgml/indexam.sgml
+++ b/doc/src/sgml/indexam.sgml
@@ -144,6 +144,7 @@ typedef struct IndexAmRoutine
     amendscan_function amendscan;
     ammarkpos_function ammarkpos;       /* can be NULL */
     amrestrpos_function amrestrpos;     /* can be NULL */
+    amskip_function amskip;     /* can be NULL */
 
     /* interface functions to support parallel index scans */
     amestimateparallelscan_function amestimateparallelscan;    /* can be NULL */
@@ -687,6 +688,15 @@ amrestrpos (IndexScanDesc scan);
 
   <para>
 <programlisting>
+bool
+amskip (IndexScanDesc scan, ScanDirection direction, int prefix);
+</programlisting>
+  Skip past all tuples where the first 'prefix' columns have the same value as
+  the last tuple returned in the current scan.
+  </para>
+
+  <para>
+<programlisting>
 Size
 amestimateparallelscan (void);
 </programlisting>
diff --git a/doc/src/sgml/indices.sgml b/doc/src/sgml/indices.sgml
index 95c0a1926c..592149f10e 100644
--- a/doc/src/sgml/indices.sgml
+++ b/doc/src/sgml/indices.sgml
@@ -1235,6 +1235,30 @@ SELECT target FROM tests WHERE subject = 'some-subject' AND success;
    and later will recognize such cases and allow index-only scans to be
    generated, but older versions will not.
   </para>
+
+  <sect2 id="indexes-index-skip-scans">
+    <title>Index Skip Scans</title>
+
+    <indexterm zone="indexes-index-skip-scans">
+      <primary>index</primary>
+      <secondary>index-skip scans</secondary>
+    </indexterm>
+    <indexterm zone="indexes-index-skip-scans">
+      <primary>index-skip scan</primary>
+    </indexterm>
+
+    <para>
+     In case if index scan is used to retrieve the distinct values of a column
+     efficiently, it can be not very efficient, since it requires to scan all
+     the equal values of a key. In such cases planner will consider apply index
+     skip scan approach, which is based on the idea of
+     <ulink url="https://wiki.postgresql.org/wiki/Free_Space_Map_Problems";
+     Loose index scan</ulink>. Rather than scanning all equal values of a key,
+     as soon as a new value is found, it will search for a larger value on the
+     same index page, and if not found, restart the search by looking for a
+     larger value. This is much faster when the index has many equal keys.
+    </para>
+  </sect2>
  </sect1>
 
 
diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c
index ae7b729edd..233ea9e5ec 100644
--- a/src/backend/access/brin/brin.c
+++ b/src/backend/access/brin/brin.c
@@ -109,6 +109,7 @@ brinhandler(PG_FUNCTION_ARGS)
 	amroutine->ambulkdelete = brinbulkdelete;
 	amroutine->amvacuumcleanup = brinvacuumcleanup;
 	amroutine->amcanreturn = NULL;
+	amroutine->amskip = NULL;
 	amroutine->amcostestimate = brincostestimate;
 	amroutine->amoptions = brinoptions;
 	amroutine->amproperty = NULL;
diff --git a/src/backend/access/gin/ginutil.c b/src/backend/access/gin/ginutil.c
index cf9699ad18..9817f34c34 100644
--- a/src/backend/access/gin/ginutil.c
+++ b/src/backend/access/gin/ginutil.c
@@ -61,6 +61,7 @@ ginhandler(PG_FUNCTION_ARGS)
 	amroutine->ambulkdelete = ginbulkdelete;
 	amroutine->amvacuumcleanup = ginvacuumcleanup;
 	amroutine->amcanreturn = NULL;
+	amroutine->amskip = NULL;
 	amroutine->amcostestimate = gincostestimate;
 	amroutine->amoptions = ginoptions;
 	amroutine->amproperty = NULL;
diff --git a/src/backend/access/gist/gist.c b/src/backend/access/gist/gist.c
index 470b121e7d..328c17f13a 100644
--- a/src/backend/access/gist/gist.c
+++ b/src/backend/access/gist/gist.c
@@ -83,6 +83,7 @@ gisthandler(PG_FUNCTION_ARGS)
 	amroutine->ambulkdelete = gistbulkdelete;
 	amroutine->amvacuumcleanup = gistvacuumcleanup;
 	amroutine->amcanreturn = gistcanreturn;
+	amroutine->amskip = NULL;
 	amroutine->amcostestimate = gistcostestimate;
 	amroutine->amoptions = gistoptions;
 	amroutine->amproperty = gistproperty;
diff --git a/src/backend/access/hash/hash.c b/src/backend/access/hash/hash.c
index e9f2c84af1..b7e9a1e949 100644
--- a/src/backend/access/hash/hash.c
+++ b/src/backend/access/hash/hash.c
@@ -82,6 +82,7 @@ hashhandler(PG_FUNCTION_ARGS)
 	amroutine->ambulkdelete = hashbulkdelete;
 	amroutine->amvacuumcleanup = hashvacuumcleanup;
 	amroutine->amcanreturn = NULL;
+	amroutine->amskip = NULL;
 	amroutine->amcostestimate = hashcostestimate;
 	amroutine->amoptions = hashoptions;
 	amroutine->amproperty = NULL;
diff --git a/src/backend/access/index/indexam.c b/src/backend/access/index/indexam.c
index aefdd2916d..1c2def162c 100644
--- a/src/backend/access/index/indexam.c
+++ b/src/backend/access/index/indexam.c
@@ -33,6 +33,7 @@
  *		index_can_return	- does index support index-only scans?
  *		index_getprocid - get a support procedure OID
  *		index_getprocinfo - get a support procedure's lookup info
+ *		index_skip		- advance past duplicate key values in a scan
  *
  * NOTES
  *		This file contains the index_ routines which used
@@ -730,6 +731,21 @@ index_can_return(Relation indexRelation, int attno)
 	return indexRelation->rd_indam->amcanreturn(indexRelation, attno);
 }
 
+/* ----------------
+ *		index_skip
+ *
+ *		Skip past all tuples where the first 'prefix' columns have the
+ *		same value as the last tuple returned in the current scan.
+ * ----------------
+ */
+bool
+index_skip(IndexScanDesc scan, ScanDirection direction, int prefix)
+{
+	SCAN_CHECKS;
+
+	return scan->indexRelation->rd_indam->amskip(scan, direction, prefix);
+}
+
 /* ----------------
  *		index_getprocid
  *
diff --git a/src/backend/access/nbtree/nbtree.c b/src/backend/access/nbtree/nbtree.c
index 85e54ac44b..3e50abd6b0 100644
--- a/src/backend/access/nbtree/nbtree.c
+++ b/src/backend/access/nbtree/nbtree.c
@@ -131,6 +131,7 @@ bthandler(PG_FUNCTION_ARGS)
 	amroutine->ambulkdelete = btbulkdelete;
 	amroutine->amvacuumcleanup = btvacuumcleanup;
 	amroutine->amcanreturn = btcanreturn;
+	amroutine->amskip = btskip;
 	amroutine->amcostestimate = btcostestimate;
 	amroutine->amoptions = btoptions;
 	amroutine->amproperty = btproperty;
@@ -380,6 +381,8 @@ btbeginscan(Relation rel, int nkeys, int norderbys)
 	 */
 	so->currTuples = so->markTuples = NULL;
 
+	so->skipScanKey = NULL;
+
 	scan->xs_itupdesc = RelationGetDescr(rel);
 
 	scan->opaque = so;
@@ -447,6 +450,15 @@ btrescan(IndexScanDesc scan, ScanKey scankey, int nscankeys,
 	_bt_preprocess_array_keys(scan);
 }
 
+/*
+ * btskip() -- skip to the beginning of the next key prefix
+ */
+bool
+btskip(IndexScanDesc scan, ScanDirection direction, int prefix)
+{
+	return _bt_skip(scan, direction, prefix);
+}
+
 /*
  *	btendscan() -- close down a scan
  */
diff --git a/src/backend/access/nbtree/nbtsearch.c b/src/backend/access/nbtree/nbtsearch.c
index 1f809c24a1..44d2a3caf8 100644
--- a/src/backend/access/nbtree/nbtsearch.c
+++ b/src/backend/access/nbtree/nbtsearch.c
@@ -37,7 +37,10 @@ static bool _bt_parallel_readpage(IndexScanDesc scan, BlockNumber blkno,
 static Buffer _bt_walk_left(Relation rel, Buffer buf, Snapshot snapshot);
 static bool _bt_endpoint(IndexScanDesc scan, ScanDirection dir);
 static inline void _bt_initialize_more_data(BTScanOpaque so, ScanDirection dir);
-
+static inline void _bt_update_skip_scankeys(IndexScanDesc scan,
+											Relation indexRel);
+static inline bool _bt_scankey_within_page(IndexScanDesc scan, BTScanInsert key,
+										Buffer buf, ScanDirection dir);
 
 /*
  *	_bt_drop_lock_and_maybe_pin()
@@ -1380,6 +1383,184 @@ _bt_next(IndexScanDesc scan, ScanDirection dir)
 	return true;
 }
 
+/*
+ *  _bt_skip() -- Skip items that have the same prefix as the most recently
+ * fetched index tuple.  The current position is set so that a subsequent call
+ * to _bt_next will fetch the first tuple that differs in the leading 'prefix'
+ * keys.
+ */
+bool
+_bt_skip(IndexScanDesc scan, ScanDirection dir, int prefix)
+{
+	BTScanOpaque so = (BTScanOpaque) scan->opaque;
+	BTStack stack;
+	Buffer buf;
+	OffsetNumber offnum;
+	BTScanPosItem *currItem;
+	Relation 	 indexRel = scan->indexRelation;
+
+	/* We want to return tuples, and we need a starting point */
+	Assert(scan->xs_want_itup);
+	Assert(scan->xs_itup);
+
+	/*
+	 * If skipScanKey is NULL then we initialize it with _bt_mkscankey,
+	 * otherwise we will just update the sk_flags / sk_argument elements
+	 * in order to eliminate repeated free/realloc.
+	 */
+	if (so->skipScanKey == NULL)
+	{
+		so->skipScanKey = _bt_mkscankey(indexRel, scan->xs_itup);
+		so->skipScanKey->keysz = prefix;
+		so->skipScanKey->scantid = NULL;
+	}
+	else
+	{
+		_bt_update_skip_scankeys(scan, indexRel);
+	}
+
+	/* Check if the next unique key can be found within the current page */
+	if (BTScanPosIsValid(so->currPos) &&
+		_bt_scankey_within_page(scan, so->skipScanKey, so->currPos.buf, dir))
+	{
+		bool keyFound = false;
+
+		LockBuffer(buf, BT_READ);
+		offnum = _bt_binsrch(scan->indexRelation, so->skipScanKey, buf);
+
+		/* Lock the page for SERIALIZABLE transactions */
+		PredicateLockPage(scan->indexRelation, BufferGetBlockNumber(buf),
+						  scan->xs_snapshot);
+
+		/* We know in which direction to look */
+		_bt_initialize_more_data(so, dir);
+
+		if (ScanDirectionIsForward(dir))
+		{
+			/* Move back for _bt_next */
+			offnum = OffsetNumberPrev(offnum);
+		}
+
+		/* Now read the data */
+		keyFound = _bt_readpage(scan, dir, offnum);
+		_bt_drop_lock_and_maybe_pin(scan, &so->currPos);
+
+		if (keyFound)
+		{
+			/* set IndexTuple */
+			currItem = &so->currPos.items[so->currPos.itemIndex];
+			scan->xs_heaptid = currItem->heapTid;
+			if (scan->xs_want_itup)
+				scan->xs_itup = (IndexTuple) (so->currTuples + currItem->tupleOffset);
+			return true;
+		}
+	}
+
+	if (BTScanPosIsValid(so->currPos))
+	{
+		ReleaseBuffer(so->currPos.buf);
+		so->currPos.buf = InvalidBuffer;
+	}
+
+	/*
+	 * We haven't found scan key within the current page, so let's scan from
+	 * the root. Use _bt_search and _bt_binsrch to get the buffer and offset
+	 * number
+	 */
+	so->skipScanKey->nextkey = ScanDirectionIsForward(dir);
+	stack = _bt_search(scan->indexRelation, so->skipScanKey,
+					   &buf, BT_READ, scan->xs_snapshot);
+	_bt_freestack(stack);
+	so->currPos.buf = buf;
+	if (ScanDirectionIsForward(dir))
+	{
+		offnum = _bt_binsrch(scan->indexRelation, so->skipScanKey, buf);
+	}
+	else
+	{
+		/* For backward scan finding offnum is more involved. It is wrong to
+		 * just use binary search, since we will find the last item from the
+		 * sequence of equal items, and we need the first one. Otherwise e.g.
+		 * backward cursor scan will return an incorrect value. */
+		offnum = _bt_binsrch(scan->indexRelation, so->skipScanKey, buf);
+		_bt_drop_lock_and_maybe_pin(scan, &so->currPos);
+
+		/* One step back to find a previous value */
+		if (_bt_next(scan, dir))
+		{
+			_bt_update_skip_scankeys(scan, indexRel);
+
+			/* And now find the last item from the sequence for the current,
+			 * value with the intention do OffsetNumberNext. As a result we
+			 * end up on a first element from the sequence. */
+			if (_bt_scankey_within_page(scan, so->skipScanKey,
+										so->currPos.buf, dir))
+			{
+				offnum = _bt_binsrch(scan->indexRelation, so->skipScanKey, buf);
+			}
+			else
+			{
+				ReleaseBuffer(so->currPos.buf);
+				so->currPos.buf = InvalidBuffer;
+
+				stack = _bt_search(scan->indexRelation, so->skipScanKey,
+								   &buf, BT_READ, scan->xs_snapshot);
+				_bt_freestack(stack);
+				so->currPos.buf = buf;
+				offnum = _bt_binsrch(scan->indexRelation, so->skipScanKey, buf);
+			}
+		}
+		else
+		{
+			pfree(so->skipScanKey);
+			so->skipScanKey = NULL;
+			return false;
+		}
+	}
+
+	/* Lock the page for SERIALIZABLE transactions */
+	PredicateLockPage(scan->indexRelation, BufferGetBlockNumber(buf),
+					  scan->xs_snapshot);
+
+	/* We know in which direction to look */
+	_bt_initialize_more_data(so, dir);
+
+	if (ScanDirectionIsForward(dir))
+		/* Move back for _bt_next */
+		offnum = OffsetNumberPrev(offnum);
+	else
+		offnum = OffsetNumberNext(offnum);
+
+	/* Now read the data */
+	if (!_bt_readpage(scan, dir, offnum))
+	{
+		/*
+		 * There's no actually-matching data on this page.  Try to advance to
+		 * the next page.  Return false if there's no matching data at all.
+		 */
+		LockBuffer(so->currPos.buf, BUFFER_LOCK_UNLOCK);
+		if (!_bt_steppage(scan, dir))
+		{
+			pfree(so->skipScanKey);
+			so->skipScanKey = NULL;
+			return false;
+		}
+	}
+	else
+	{
+		/* Drop the lock, and maybe the pin, on the current page */
+		_bt_drop_lock_and_maybe_pin(scan, &so->currPos);
+	}
+
+	/* And set IndexTuple */
+	currItem = &so->currPos.items[so->currPos.itemIndex];
+	scan->xs_heaptid = currItem->heapTid;
+	if (scan->xs_want_itup)
+		scan->xs_itup = (IndexTuple) (so->currTuples + currItem->tupleOffset);
+
+	return true;
+}
+
 /*
  *	_bt_readpage() -- Load data from current index page into so->currPos
  *
@@ -2249,3 +2430,44 @@ _bt_initialize_more_data(BTScanOpaque so, ScanDirection dir)
 	so->numKilled = 0;			/* just paranoia */
 	so->markItemIndex = -1;		/* ditto */
 }
+
+static inline void
+_bt_update_skip_scankeys(IndexScanDesc scan, Relation indexRel)
+{
+	TupleDesc		itupdesc;
+	int				indnkeyatts, i;
+	BTScanOpaque 	so = (BTScanOpaque) scan->opaque;
+	ScanKey			scankeys = so->skipScanKey->scankeys;
+
+	itupdesc = RelationGetDescr(indexRel);
+	indnkeyatts = IndexRelationGetNumberOfKeyAttributes(indexRel);
+	for (i = 0; i < indnkeyatts; i++)
+	{
+		Datum datum;
+		bool null;
+		int flags;
+
+		datum = index_getattr(scan->xs_itup, i + 1, itupdesc, &null);
+		flags = (null ? SK_ISNULL : 0) |
+				(indexRel->rd_indoption[i] << SK_BT_INDOPTION_SHIFT);
+		scankeys[i].sk_flags = flags;
+		scankeys[i].sk_argument = datum;
+	}
+}
+
+static inline bool
+_bt_scankey_within_page(IndexScanDesc scan, BTScanInsert key,
+						Buffer buf, ScanDirection dir)
+{
+	OffsetNumber low, high, compare_offset;
+	Page page = BufferGetPage(buf);
+	BTPageOpaque opaque = (BTPageOpaque) PageGetSpecialPointer(page);
+	int 		 compare_value = ScanDirectionIsForward(dir) ? 0 : 1;
+
+	low = P_FIRSTDATAKEY(opaque);
+	high = PageGetMaxOffsetNumber(page);
+	compare_offset = ScanDirectionIsForward(dir) ? high : low;
+
+	return _bt_compare(scan->indexRelation,
+					   key, page, compare_offset) > compare_value;
+}
diff --git a/src/backend/access/spgist/spgutils.c b/src/backend/access/spgist/spgutils.c
index 45472db147..dc151ecf09 100644
--- a/src/backend/access/spgist/spgutils.c
+++ b/src/backend/access/spgist/spgutils.c
@@ -64,6 +64,7 @@ spghandler(PG_FUNCTION_ARGS)
 	amroutine->ambulkdelete = spgbulkdelete;
 	amroutine->amvacuumcleanup = spgvacuumcleanup;
 	amroutine->amcanreturn = spgcanreturn;
+	amroutine->amskip = NULL;
 	amroutine->amcostestimate = spgcostestimate;
 	amroutine->amoptions = spgoptions;
 	amroutine->amproperty = spgproperty;
diff --git a/src/backend/commands/explain.c b/src/backend/commands/explain.c
index 92969636b7..c750437cc6 100644
--- a/src/backend/commands/explain.c
+++ b/src/backend/commands/explain.c
@@ -1373,6 +1373,14 @@ ExplainNode(PlanState *planstate, List *ancestors,
 			{
 				IndexOnlyScan *indexonlyscan = (IndexOnlyScan *) plan;
 
+				if (indexonlyscan->skipPrefixSize > 0)
+				{
+					if (es->format != EXPLAIN_FORMAT_TEXT)
+						ExplainPropertyInteger("Distinct Prefix", NULL,
+											   indexonlyscan->skipPrefixSize,
+											   es);
+				}
+
 				ExplainIndexScanDetails(indexonlyscan->indexid,
 										indexonlyscan->indexorderdir,
 										es);
@@ -1595,6 +1603,10 @@ ExplainNode(PlanState *planstate, List *ancestors,
 										   planstate, es);
 			break;
 		case T_IndexOnlyScan:
+			if (((IndexOnlyScan *) plan)->skipPrefixSize > 0)
+			{
+				ExplainPropertyText("Scan mode", "Skip scan", es);
+			}
 			show_scan_qual(((IndexOnlyScan *) plan)->indexqual,
 						   "Index Cond", planstate, ancestors, es);
 			if (((IndexOnlyScan *) plan)->indexqual)
diff --git a/src/backend/executor/nodeIndexonlyscan.c b/src/backend/executor/nodeIndexonlyscan.c
index 8a4d795d1a..15e2ff7b1b 100644
--- a/src/backend/executor/nodeIndexonlyscan.c
+++ b/src/backend/executor/nodeIndexonlyscan.c
@@ -115,6 +115,24 @@ IndexOnlyNext(IndexOnlyScanState *node)
 						 node->ioss_NumOrderByKeys);
 	}
 
+	/*
+	 * Check if we need to skip to the next key prefix, because we've been
+	 * asked to implement DISTINCT.
+	 */
+	if (node->ioss_SkipPrefixSize > 0 && node->ioss_FirstTupleEmitted)
+	{
+		if (!index_skip(scandesc, direction, node->ioss_SkipPrefixSize))
+		{
+			/* Reached end of index. At this point currPos is invalidated,
+			 * and we need to reset ioss_FirstTupleEmitted, since otherwise
+			 * after going backwards, reaching the end of index, and going
+			 * forward again we apply skip again. It would be incorrect and
+			 * lead to an extra skipped item. */
+			node->ioss_FirstTupleEmitted = false;
+			return ExecClearTuple(slot);
+		}
+	}
+
 	/*
 	 * OK, now that we have what we need, fetch the next tuple.
 	 */
@@ -253,6 +271,8 @@ IndexOnlyNext(IndexOnlyScanState *node)
 							  ItemPointerGetBlockNumber(tid),
 							  estate->es_snapshot);
 
+		node->ioss_FirstTupleEmitted = true;
+
 		return slot;
 	}
 
@@ -503,6 +523,8 @@ ExecInitIndexOnlyScan(IndexOnlyScan *node, EState *estate, int eflags)
 	indexstate->ss.ps.plan = (Plan *) node;
 	indexstate->ss.ps.state = estate;
 	indexstate->ss.ps.ExecProcNode = ExecIndexOnlyScan;
+	indexstate->ioss_SkipPrefixSize = node->skipPrefixSize;
+	indexstate->ioss_FirstTupleEmitted = false;
 
 	/*
 	 * Miscellaneous initialization
diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c
index 78deade89b..421719cbb7 100644
--- a/src/backend/nodes/copyfuncs.c
+++ b/src/backend/nodes/copyfuncs.c
@@ -515,6 +515,7 @@ _copyIndexOnlyScan(const IndexOnlyScan *from)
 	COPY_NODE_FIELD(indexorderby);
 	COPY_NODE_FIELD(indextlist);
 	COPY_SCALAR_FIELD(indexorderdir);
+	COPY_SCALAR_FIELD(skipPrefixSize);
 
 	return newnode;
 }
diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
index 8400dd319e..f99ed30632 100644
--- a/src/backend/nodes/outfuncs.c
+++ b/src/backend/nodes/outfuncs.c
@@ -573,6 +573,7 @@ _outIndexOnlyScan(StringInfo str, const IndexOnlyScan *node)
 	WRITE_NODE_FIELD(indexorderby);
 	WRITE_NODE_FIELD(indextlist);
 	WRITE_ENUM_FIELD(indexorderdir, ScanDirection);
+	WRITE_INT_FIELD(skipPrefixSize);
 }
 
 static void
@@ -2208,6 +2209,7 @@ _outPlannerInfo(StringInfo str, const PlannerInfo *node)
 	WRITE_NODE_FIELD(group_pathkeys);
 	WRITE_NODE_FIELD(window_pathkeys);
 	WRITE_NODE_FIELD(distinct_pathkeys);
+	WRITE_NODE_FIELD(uniq_distinct_pathkeys);
 	WRITE_NODE_FIELD(sort_pathkeys);
 	WRITE_NODE_FIELD(processed_tlist);
 	WRITE_NODE_FIELD(minmax_aggs);
diff --git a/src/backend/nodes/readfuncs.c b/src/backend/nodes/readfuncs.c
index 6c2626ee62..5e431bec7b 100644
--- a/src/backend/nodes/readfuncs.c
+++ b/src/backend/nodes/readfuncs.c
@@ -1806,6 +1806,7 @@ _readIndexOnlyScan(void)
 	READ_NODE_FIELD(indexorderby);
 	READ_NODE_FIELD(indextlist);
 	READ_ENUM_FIELD(indexorderdir, ScanDirection);
+	READ_INT_FIELD(skipPrefixSize);
 
 	READ_DONE();
 }
diff --git a/src/backend/optimizer/path/costsize.c b/src/backend/optimizer/path/costsize.c
index a2a9b1f7be..6e0fe90e5c 100644
--- a/src/backend/optimizer/path/costsize.c
+++ b/src/backend/optimizer/path/costsize.c
@@ -124,6 +124,7 @@ int			max_parallel_workers_per_gather = 2;
 bool		enable_seqscan = true;
 bool		enable_indexscan = true;
 bool		enable_indexonlyscan = true;
+bool		enable_indexskipscan = true;
 bool		enable_bitmapscan = true;
 bool		enable_tidscan = true;
 bool		enable_sort = true;
diff --git a/src/backend/optimizer/path/pathkeys.c b/src/backend/optimizer/path/pathkeys.c
index 08b5061612..af7d9c4270 100644
--- a/src/backend/optimizer/path/pathkeys.c
+++ b/src/backend/optimizer/path/pathkeys.c
@@ -29,6 +29,7 @@
 #include "utils/lsyscache.h"
 
 
+static bool pathkey_is_unique(PathKey *new_pathkey, List *pathkeys);
 static bool pathkey_is_redundant(PathKey *new_pathkey, List *pathkeys);
 static bool matches_boolean_partition_clause(RestrictInfo *rinfo,
 											 RelOptInfo *partrel,
@@ -94,6 +95,30 @@ make_canonical_pathkey(PlannerInfo *root,
 	return pk;
 }
 
+/*
+ * pathkey_is_unique
+ *	   Part of pathkey_is_redundant, that is reponsible for the case, when the
+ *	   new pathkey's equivalence class is the same as that of any existing
+ *	   member of the pathkey list.
+ */
+static bool
+pathkey_is_unique(PathKey *new_pathkey, List *pathkeys)
+{
+	EquivalenceClass *new_ec = new_pathkey->pk_eclass;
+	ListCell   *lc;
+
+	/* If same EC already used in list, then redundant */
+	foreach(lc, pathkeys)
+	{
+		PathKey    *old_pathkey = (PathKey *) lfirst(lc);
+
+		if (new_ec == old_pathkey->pk_eclass)
+			return true;
+	}
+
+	return false;
+}
+
 /*
  * pathkey_is_redundant
  *	   Is a pathkey redundant with one already in the given list?
@@ -133,22 +158,12 @@ static bool
 pathkey_is_redundant(PathKey *new_pathkey, List *pathkeys)
 {
 	EquivalenceClass *new_ec = new_pathkey->pk_eclass;
-	ListCell   *lc;
 
 	/* Check for EC containing a constant --- unconditionally redundant */
 	if (EC_MUST_BE_REDUNDANT(new_ec))
 		return true;
 
-	/* If same EC already used in list, then redundant */
-	foreach(lc, pathkeys)
-	{
-		PathKey    *old_pathkey = (PathKey *) lfirst(lc);
-
-		if (new_ec == old_pathkey->pk_eclass)
-			return true;
-	}
-
-	return false;
+	return pathkey_is_unique(new_pathkey, pathkeys);
 }
 
 /*
@@ -1096,6 +1111,53 @@ make_pathkeys_for_sortclauses(PlannerInfo *root,
 	return pathkeys;
 }
 
+/*
+ * make_pathkeys_for_distinctclauses
+ *		Generate a pathkeys list for distinct clauses, that represents the sort
+ *		order specified by a list of SortGroupClauses. Similar to
+ *		make_pathkeys_for_sortclauses, but allows to specify if we need to
+ *		check the full redundancy, or just uniqueness.
+ */
+List *
+make_pathkeys_for_distinctclauses(PlannerInfo *root,
+								  List *distinctclauses,
+								  List *tlist, bool checkRedundant)
+{
+	List	   *pathkeys = NIL;
+	ListCell   *l;
+
+	foreach(l, distinctclauses)
+	{
+		SortGroupClause *sortcl = (SortGroupClause *) lfirst(l);
+		Expr	   *sortkey;
+		PathKey    *pathkey;
+
+		sortkey = (Expr *) get_sortgroupclause_expr(sortcl, tlist);
+		Assert(OidIsValid(sortcl->sortop));
+		pathkey = make_pathkey_from_sortop(root,
+										   sortkey,
+										   root->nullable_baserels,
+										   sortcl->sortop,
+										   sortcl->nulls_first,
+										   sortcl->tleSortGroupRef,
+										   true);
+
+		/* Canonical form eliminates redundant ordering keys */
+		if (checkRedundant)
+		{
+			if (!pathkey_is_redundant(pathkey, pathkeys))
+				pathkeys = lappend(pathkeys, pathkey);
+		}
+		else
+		{
+			if (!pathkey_is_unique(pathkey, pathkeys))
+				pathkeys = lappend(pathkeys, pathkey);
+		}
+	}
+	return pathkeys;
+}
+
+
 /****************************************************************************
  *		PATHKEYS AND MERGECLAUSES
  ****************************************************************************/
diff --git a/src/backend/optimizer/plan/createplan.c b/src/backend/optimizer/plan/createplan.c
index 608d5adfed..b578dcca20 100644
--- a/src/backend/optimizer/plan/createplan.c
+++ b/src/backend/optimizer/plan/createplan.c
@@ -180,7 +180,8 @@ static IndexOnlyScan *make_indexonlyscan(List *qptlist, List *qpqual,
 										 Index scanrelid, Oid indexid,
 										 List *indexqual, List *indexorderby,
 										 List *indextlist,
-										 ScanDirection indexscandir);
+										 ScanDirection indexscandir,
+										 int skipprefix);
 static BitmapIndexScan *make_bitmap_indexscan(Index scanrelid, Oid indexid,
 											  List *indexqual,
 											  List *indexqualorig);
@@ -2903,7 +2904,8 @@ create_indexscan_plan(PlannerInfo *root,
 												fixed_indexquals,
 												fixed_indexorderbys,
 												best_path->indexinfo->indextlist,
-												best_path->indexscandir);
+												best_path->indexscandir,
+												best_path->indexskipprefix);
 	else
 		scan_plan = (Scan *) make_indexscan(tlist,
 											qpqual,
@@ -5179,7 +5181,8 @@ make_indexonlyscan(List *qptlist,
 				   List *indexqual,
 				   List *indexorderby,
 				   List *indextlist,
-				   ScanDirection indexscandir)
+				   ScanDirection indexscandir,
+				   int skipPrefixSize)
 {
 	IndexOnlyScan *node = makeNode(IndexOnlyScan);
 	Plan	   *plan = &node->scan.plan;
@@ -5194,6 +5197,7 @@ make_indexonlyscan(List *qptlist,
 	node->indexorderby = indexorderby;
 	node->indextlist = indextlist;
 	node->indexorderdir = indexscandir;
+	node->skipPrefixSize = skipPrefixSize;
 
 	return node;
 }
diff --git a/src/backend/optimizer/plan/planagg.c b/src/backend/optimizer/plan/planagg.c
index 9381939c82..ed52139839 100644
--- a/src/backend/optimizer/plan/planagg.c
+++ b/src/backend/optimizer/plan/planagg.c
@@ -505,6 +505,7 @@ minmax_qp_callback(PlannerInfo *root, void *extra)
 	root->group_pathkeys = NIL;
 	root->window_pathkeys = NIL;
 	root->distinct_pathkeys = NIL;
+	root->uniq_distinct_pathkeys = NIL;
 
 	root->sort_pathkeys =
 		make_pathkeys_for_sortclauses(root,
diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c
index cb897cc7f4..ed16b62dba 100644
--- a/src/backend/optimizer/plan/planner.c
+++ b/src/backend/optimizer/plan/planner.c
@@ -3615,12 +3615,21 @@ standard_qp_callback(PlannerInfo *root, void *extra)
 
 	if (parse->distinctClause &&
 		grouping_is_sortable(parse->distinctClause))
+	{
+		root->uniq_distinct_pathkeys =
+			make_pathkeys_for_distinctclauses(root,
+											  parse->distinctClause,
+											  tlist, false);
 		root->distinct_pathkeys =
-			make_pathkeys_for_sortclauses(root,
-										  parse->distinctClause,
-										  tlist);
+			make_pathkeys_for_distinctclauses(root,
+											  parse->distinctClause,
+											  tlist, true);
+	}
 	else
+	{
 		root->distinct_pathkeys = NIL;
+		root->uniq_distinct_pathkeys = NIL;
+	}
 
 	root->sort_pathkeys =
 		make_pathkeys_for_sortclauses(root,
@@ -4802,11 +4811,63 @@ create_distinct_paths(PlannerInfo *root,
 
 			if (pathkeys_contained_in(needed_pathkeys, path->pathkeys))
 			{
+				ListCell   		*lc;
+				IndexOptInfo 	*index = NULL;
+				bool 			differentColumnsOrder = false;
+				int 			i = 0;
+
 				add_path(distinct_rel, (Path *)
 						 create_upper_unique_path(root, distinct_rel,
 												  path,
 												  list_length(root->distinct_pathkeys),
 												  numDistinctRows));
+
+				/* Also consider a skip scan, if possible. */
+				if(IsA(path, IndexPath))
+					index = ((IndexPath *) path)->indexinfo;
+				else
+					continue;
+
+				/*
+				 * The order of columns in the index should be the same, as for
+				 * unique distincs pathkeys, otherwise we cannot use _bt_search
+				 * in the skip implementation - this can lead to a missing
+				 * records.
+				 */
+				foreach(lc, root->uniq_distinct_pathkeys)
+				{
+					PathKey *pathKey = lfirst_node(PathKey, lc);
+					EquivalenceMember *em =
+						lfirst_node(EquivalenceMember,
+									list_head(pathKey->pk_eclass->ec_members));
+					Var *var = (Var *) em->em_expr;
+
+					Assert(i < index->ncolumns);
+
+					if (index->indexkeys[i] != var->varattno)
+					{
+						differentColumnsOrder = true;
+						break;
+					}
+
+					i++;
+				}
+
+				if (path->pathtype == T_IndexOnlyScan &&
+					enable_indexskipscan &&
+					index->amcanskip &&
+					root->distinct_pathkeys != NIL &&
+					!differentColumnsOrder)
+				{
+					int distinctPrefixKeys =
+						list_length(root->uniq_distinct_pathkeys);
+					add_path(distinct_rel, (Path *)
+							 create_skipscan_unique_path(root,
+														 distinct_rel,
+														 path,
+														 distinctPrefixKeys,
+														 numDistinctRows));
+				}
 			}
 		}
 
diff --git a/src/backend/optimizer/util/pathnode.c b/src/backend/optimizer/util/pathnode.c
index d884d2bb00..df9b57215f 100644
--- a/src/backend/optimizer/util/pathnode.c
+++ b/src/backend/optimizer/util/pathnode.c
@@ -2928,6 +2928,46 @@ create_upper_unique_path(PlannerInfo *root,
 	return pathnode;
 }
 
+/*
+ * create_skipscan_unique_path
+ *	  Creates a pathnode the same as an existing IndexPath except based on
+ *	  skipping duplicate values.  This may or may not be cheaper than using
+ *	  create_upper_unique_path.
+ *
+ * The input path must be an IndexPath for an index that supports amskip.
+ */
+IndexPath *
+create_skipscan_unique_path(PlannerInfo *root,
+							RelOptInfo *rel,
+							Path *basepath,
+							int distinctPrefixKeys,
+							double numGroups)
+{
+	IndexPath *pathnode = makeNode(IndexPath);
+
+	Assert(IsA(basepath, IndexPath));
+
+	/* We don't want to modify basepath, so make a copy. */
+	memcpy(pathnode, basepath, sizeof(IndexPath));
+
+	/* The size of the prefix we'll use for skipping. */
+	Assert(pathnode->indexinfo->amcanskip);
+	Assert(distinctPrefixKeys > 0);
+	/*Assert(distinctPrefixKeys <= list_length(pathnode->path.pathkeys));*/
+	pathnode->indexskipprefix = distinctPrefixKeys;
+
+	/*
+	 * The cost to skip to each distinct value should be roughly the same as
+	 * the cost of finding the first key times the number of distinct values
+	 * we expect to find.
+	 */
+	pathnode->path.startup_cost = basepath->startup_cost;
+	pathnode->path.total_cost = basepath->startup_cost * numGroups;
+	pathnode->path.rows = numGroups;
+
+	return pathnode;
+}
+
 /*
  * create_agg_path
  *	  Creates a pathnode that represents performing aggregation/grouping
diff --git a/src/backend/optimizer/util/plancat.c b/src/backend/optimizer/util/plancat.c
index 2405acbf6f..0f0bdad2ac 100644
--- a/src/backend/optimizer/util/plancat.c
+++ b/src/backend/optimizer/util/plancat.c
@@ -269,6 +269,7 @@ get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent,
 			info->amoptionalkey = amroutine->amoptionalkey;
 			info->amsearcharray = amroutine->amsearcharray;
 			info->amsearchnulls = amroutine->amsearchnulls;
+			info->amcanskip = (amroutine->amskip != NULL);
 			info->amcanparallel = amroutine->amcanparallel;
 			info->amhasgettuple = (amroutine->amgettuple != NULL);
 			info->amhasgetbitmap = amroutine->amgetbitmap != NULL &&
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 1208eb9a68..007c8ac14e 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -912,6 +912,15 @@ static struct config_bool ConfigureNamesBool[] =
 		true,
 		NULL, NULL, NULL
 	},
+	{
+		{"enable_indexskipscan", PGC_USERSET, QUERY_TUNING_METHOD,
+			gettext_noop("Enables the planner's use of index-skip-scan plans."),
+			NULL
+		},
+		&enable_indexskipscan,
+		true,
+		NULL, NULL, NULL
+	},
 	{
 		{"enable_bitmapscan", PGC_USERSET, QUERY_TUNING_METHOD,
 			gettext_noop("Enables the planner's use of bitmap-scan plans."),
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index 5ee5e09ddf..99facc8f50 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -351,6 +351,7 @@
 #enable_hashjoin = on
 #enable_indexscan = on
 #enable_indexonlyscan = on
+#enable_indexskipscan = on
 #enable_material = on
 #enable_mergejoin = on
 #enable_nestloop = on
diff --git a/src/include/access/amapi.h b/src/include/access/amapi.h
index 6e3db06eed..34033c5486 100644
--- a/src/include/access/amapi.h
+++ b/src/include/access/amapi.h
@@ -130,6 +130,10 @@ typedef void (*amrescan_function) (IndexScanDesc scan,
 typedef bool (*amgettuple_function) (IndexScanDesc scan,
 									 ScanDirection direction);
 
+/* skip past duplicates in a given prefix */
+typedef bool (*amskip_function) (IndexScanDesc scan,
+								 ScanDirection dir, int prefix);
+
 /* fetch all valid tuples */
 typedef int64 (*amgetbitmap_function) (IndexScanDesc scan,
 									   TIDBitmap *tbm);
@@ -225,6 +229,7 @@ typedef struct IndexAmRoutine
 	amendscan_function amendscan;
 	ammarkpos_function ammarkpos;	/* can be NULL */
 	amrestrpos_function amrestrpos; /* can be NULL */
+	amskip_function amskip;				/* can be NULL */
 
 	/* interface functions to support parallel index scans */
 	amestimateparallelscan_function amestimateparallelscan; /* can be NULL */
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index 8c053be2ca..2e79098b85 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -173,6 +173,7 @@ extern IndexBulkDeleteResult *index_bulk_delete(IndexVacuumInfo *info,
 extern IndexBulkDeleteResult *index_vacuum_cleanup(IndexVacuumInfo *info,
 												   IndexBulkDeleteResult *stats);
 extern bool index_can_return(Relation indexRelation, int attno);
+extern bool index_skip(IndexScanDesc scan, ScanDirection direction, int prefix);
 extern RegProcedure index_getprocid(Relation irel, AttrNumber attnum,
 									uint16 procnum);
 extern FmgrInfo *index_getprocinfo(Relation irel, AttrNumber attnum,
diff --git a/src/include/access/nbtree.h b/src/include/access/nbtree.h
index a3583f225b..247cdb8127 100644
--- a/src/include/access/nbtree.h
+++ b/src/include/access/nbtree.h
@@ -663,6 +663,9 @@ typedef struct BTScanOpaqueData
 	 */
 	int			markItemIndex;	/* itemIndex, or -1 if not valid */
 
+	/* Work space for _bt_skip */
+	BTScanInsert	skipScanKey;	/* used to control skipping */
+
 	/* keep these last in struct for efficiency */
 	BTScanPosData currPos;		/* current position data */
 	BTScanPosData markPos;		/* marked position, if any */
@@ -777,6 +780,7 @@ extern OffsetNumber _bt_binsrch_insert(Relation rel, BTInsertState insertstate);
 extern int32 _bt_compare(Relation rel, BTScanInsert key, Page page, OffsetNumber offnum);
 extern bool _bt_first(IndexScanDesc scan, ScanDirection dir);
 extern bool _bt_next(IndexScanDesc scan, ScanDirection dir);
+extern bool _bt_skip(IndexScanDesc scan, ScanDirection dir, int prefix);
 extern Buffer _bt_get_endpoint(Relation rel, uint32 level, bool rightmost,
 							   Snapshot snapshot);
 
@@ -801,6 +805,7 @@ extern void _bt_end_vacuum_callback(int code, Datum arg);
 extern Size BTreeShmemSize(void);
 extern void BTreeShmemInit(void);
 extern bytea *btoptions(Datum reloptions, bool validate);
+extern bool btskip(IndexScanDesc scan, ScanDirection dir, int prefix);
 extern bool btproperty(Oid index_oid, int attno,
 					   IndexAMProperty prop, const char *propname,
 					   bool *res, bool *isnull);
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index 99b9fa414f..01611fd411 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -1405,6 +1405,8 @@ typedef struct IndexScanState
  *		ScanDesc		   index scan descriptor
  *		TableSlot		   slot for holding tuples fetched from the table
  *		VMBuffer		   buffer in use for visibility map testing, if any
+ *		SkipPrefixSize	   number of keys for skip-based DISTINCT
+ *		FirstTupleEmitted  has the first tuple been emitted
  *		PscanLen		   size of parallel index-only scan descriptor
  * ----------------
  */
@@ -1424,6 +1426,8 @@ typedef struct IndexOnlyScanState
 	struct IndexScanDescData *ioss_ScanDesc;
 	TupleTableSlot *ioss_TableSlot;
 	Buffer		ioss_VMBuffer;
+	int         ioss_SkipPrefixSize;
+	bool		ioss_FirstTupleEmitted;
 	Size		ioss_PscanLen;
 } IndexOnlyScanState;
 
diff --git a/src/include/nodes/pathnodes.h b/src/include/nodes/pathnodes.h
index 4b7703d478..e571c84473 100644
--- a/src/include/nodes/pathnodes.h
+++ b/src/include/nodes/pathnodes.h
@@ -298,6 +298,9 @@ struct PlannerInfo
 	List	   *group_pathkeys; /* groupClause pathkeys, if any */
 	List	   *window_pathkeys;	/* pathkeys of bottom window, if any */
 	List	   *distinct_pathkeys;	/* distinctClause pathkeys, if any */
+	List	   *uniq_distinct_pathkeys;	/* unique, but not necessarily not
+										   redundant distinctClause pathkeys,
+										   if any */
 	List	   *sort_pathkeys;	/* sortClause pathkeys, if any */
 
 	List	   *part_schemes;	/* Canonicalised partition schemes used in the
@@ -829,6 +832,7 @@ struct IndexOptInfo
 	bool		amsearchnulls;	/* can AM search for NULL/NOT NULL entries? */
 	bool		amhasgettuple;	/* does AM have amgettuple interface? */
 	bool		amhasgetbitmap; /* does AM have amgetbitmap interface? */
+	bool		amcanskip;		/* can AM skip duplicate values? */
 	bool		amcanparallel;	/* does AM support parallel scan? */
 	/* Rather than include amapi.h here, we declare amcostestimate like this */
 	void		(*amcostestimate) ();	/* AM's cost estimator */
@@ -1165,6 +1169,9 @@ typedef struct Path
  * we need not recompute them when considering using the same index in a
  * bitmap index/heap scan (see BitmapHeapPath).  The costs of the IndexPath
  * itself represent the costs of an IndexScan or IndexOnlyScan plan type.
+ *
+ * 'indexskipprefix' represents the number of columns to consider for skip
+ * scans.
  *----------
  */
 typedef struct IndexPath
@@ -1177,6 +1184,7 @@ typedef struct IndexPath
 	ScanDirection indexscandir;
 	Cost		indextotalcost;
 	Selectivity indexselectivity;
+	int			indexskipprefix;
 } IndexPath;
 
 /*
diff --git a/src/include/nodes/plannodes.h b/src/include/nodes/plannodes.h
index 70f8b8e22b..b5b7d62b70 100644
--- a/src/include/nodes/plannodes.h
+++ b/src/include/nodes/plannodes.h
@@ -432,6 +432,7 @@ typedef struct IndexOnlyScan
 	List	   *indexorderby;	/* list of index ORDER BY exprs */
 	List	   *indextlist;		/* TargetEntry list describing index's cols */
 	ScanDirection indexorderdir;	/* forward or backward or don't care */
+	int			skipPrefixSize;	/* the size of the prefix for distinct scans */
 } IndexOnlyScan;
 
 /* ----------------
diff --git a/src/include/optimizer/cost.h b/src/include/optimizer/cost.h
index 9b6bdbc518..ad28c7f54a 100644
--- a/src/include/optimizer/cost.h
+++ b/src/include/optimizer/cost.h
@@ -50,6 +50,7 @@ extern PGDLLIMPORT int max_parallel_workers_per_gather;
 extern PGDLLIMPORT bool enable_seqscan;
 extern PGDLLIMPORT bool enable_indexscan;
 extern PGDLLIMPORT bool enable_indexonlyscan;
+extern PGDLLIMPORT bool enable_indexskipscan;
 extern PGDLLIMPORT bool enable_bitmapscan;
 extern PGDLLIMPORT bool enable_tidscan;
 extern PGDLLIMPORT bool enable_sort;
diff --git a/src/include/optimizer/pathnode.h b/src/include/optimizer/pathnode.h
index e70d6a3f18..fa461201a7 100644
--- a/src/include/optimizer/pathnode.h
+++ b/src/include/optimizer/pathnode.h
@@ -202,6 +202,11 @@ extern UpperUniquePath *create_upper_unique_path(PlannerInfo *root,
 												 Path *subpath,
 												 int numCols,
 												 double numGroups);
+extern IndexPath *create_skipscan_unique_path(PlannerInfo *root,
+											  RelOptInfo *rel,
+											  Path *subpath,
+											  int numCols,
+											  double numGroups);
 extern AggPath *create_agg_path(PlannerInfo *root,
 								RelOptInfo *rel,
 								Path *subpath,
diff --git a/src/include/optimizer/paths.h b/src/include/optimizer/paths.h
index 7345137d1d..a782d12a50 100644
--- a/src/include/optimizer/paths.h
+++ b/src/include/optimizer/paths.h
@@ -209,6 +209,10 @@ extern List *build_join_pathkeys(PlannerInfo *root,
 extern List *make_pathkeys_for_sortclauses(PlannerInfo *root,
 										   List *sortclauses,
 										   List *tlist);
+extern List *make_pathkeys_for_distinctclauses(PlannerInfo *root,
+											   List *sortclauses,
+											   List *tlist,
+											   bool checkRedundant);
 extern void initialize_mergeclause_eclasses(PlannerInfo *root,
 											RestrictInfo *restrictinfo);
 extern void update_mergeclause_eclasses(PlannerInfo *root,
diff --git a/src/test/regress/expected/create_index.out b/src/test/regress/expected/create_index.out
index c30e6738ba..91a8af3416 100644
--- a/src/test/regress/expected/create_index.out
+++ b/src/test/regress/expected/create_index.out
@@ -19,6 +19,7 @@ CREATE INDEX tenk1_unique1 ON tenk1 USING btree(unique1 int4_ops);
 CREATE INDEX tenk1_unique2 ON tenk1 USING btree(unique2 int4_ops);
 CREATE INDEX tenk1_hundred ON tenk1 USING btree(hundred int4_ops);
 CREATE INDEX tenk1_thous_tenthous ON tenk1 (thousand, tenthous);
+CREATE INDEX tenk1_four ON tenk1 (four);
 CREATE INDEX tenk2_unique1 ON tenk2 USING btree(unique1 int4_ops);
 CREATE INDEX tenk2_unique2 ON tenk2 USING btree(unique2 int4_ops);
 CREATE INDEX tenk2_hundred ON tenk2 USING btree(hundred int4_ops);
diff --git a/src/test/regress/expected/select_distinct.out b/src/test/regress/expected/select_distinct.out
index f3696c6d1d..17a017dc4b 100644
--- a/src/test/regress/expected/select_distinct.out
+++ b/src/test/regress/expected/select_distinct.out
@@ -244,3 +244,179 @@ SELECT null IS NOT DISTINCT FROM null as "yes";
  t
 (1 row)
 
+-- index skip scan
+SELECT DISTINCT four FROM tenk1;
+ four 
+------
+    0
+    1
+    2
+    3
+(4 rows)
+
+SELECT DISTINCT four FROM tenk1 WHERE four = 1;
+ four 
+------
+    1
+(1 row)
+
+-- check colums order
+SELECT DISTINCT four FROM tenk1 WHERE ten = 2;
+ four 
+------
+    0
+    2
+(2 rows)
+
+CREATE INDEX tenk1_four_ten on tenk1 (four, ten);
+SELECT DISTINCT four FROM tenk1 WHERE ten = 2;
+ four 
+------
+    0
+    2
+(2 rows)
+
+SELECT DISTINCT on (four, ten) four, ten FROM tenk1 WHERE four = 0;
+ four | ten 
+------+-----
+    0 |   0
+    0 |   2
+    0 |   4
+    0 |   6
+    0 |   8
+(5 rows)
+
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT DISTINCT four FROM tenk1 WHERE ten = 2;
+                      QUERY PLAN                      
+------------------------------------------------------
+ Index Only Scan using tenk1_four_ten on public.tenk1
+   Output: four
+   Scan mode: Skip scan
+   Index Cond: (tenk1.ten = 2)
+(4 rows)
+
+-- test uniq_distinct_pathkeys
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT DISTINCT on (four, ten) four, ten FROM tenk1 WHERE four = 0;
+                      QUERY PLAN                      
+------------------------------------------------------
+ Index Only Scan using tenk1_four_ten on public.tenk1
+   Output: four, ten
+   Scan mode: Skip scan
+   Index Cond: (tenk1.four = 0)
+(4 rows)
+
+DROP INDEX tenk1_four_ten;
+CREATE INDEX tenk1_ten_four on tenk1 (ten, four);
+SELECT DISTINCT four FROM tenk1 WHERE ten = 2;
+ four 
+------
+    0
+    2
+(2 rows)
+
+SELECT DISTINCT on (four, ten) four, ten FROM tenk1 WHERE ten = 2;
+ four | ten 
+------+-----
+    0 |   2
+    2 |   2
+(2 rows)
+
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT DISTINCT four FROM tenk1 WHERE ten = 2;
+                         QUERY PLAN                         
+------------------------------------------------------------
+ Unique
+   Output: four
+   ->  Index Only Scan using tenk1_ten_four on public.tenk1
+         Output: four
+         Index Cond: (tenk1.ten = 2)
+(5 rows)
+
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT DISTINCT on (four, ten) four, ten FROM tenk1 WHERE ten = 2;
+                         QUERY PLAN                         
+------------------------------------------------------------
+ Unique
+   Output: four, ten
+   ->  Index Only Scan using tenk1_ten_four on public.tenk1
+         Output: four, ten
+         Index Cond: (tenk1.ten = 2)
+(5 rows)
+
+DROP INDEX tenk1_ten_four;
+-- check projection case
+SELECT DISTINCT four, four FROM tenk1 WHERE ten = 2;
+ four | four 
+------+------
+    0 |    0
+    2 |    2
+(2 rows)
+
+SELECT DISTINCT four, 1 FROM tenk1 WHERE ten = 2;
+ four | ?column? 
+------+----------
+    2 |        1
+    0 |        1
+(2 rows)
+
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT DISTINCT four FROM tenk1;
+                    QUERY PLAN                    
+--------------------------------------------------
+ Index Only Scan using tenk1_four on public.tenk1
+   Output: four
+   Scan mode: Skip scan
+(3 rows)
+
+BEGIN;
+DECLARE c SCROLL CURSOR FOR SELECT DISTINCT four FROM tenk1;
+FETCH FROM c;
+ four 
+------
+    0
+(1 row)
+
+FETCH BACKWARD FROM c;
+ four 
+------
+(0 rows)
+
+FETCH 5 FROM c;
+ four 
+------
+    0
+    1
+    2
+    3
+(4 rows)
+
+FETCH BACKWARD 5 FROM c;
+ four 
+------
+    3
+    2
+    1
+    0
+(4 rows)
+
+FETCH 5 FROM c;
+ four 
+------
+    0
+    1
+    2
+    3
+(4 rows)
+
+FETCH BACKWARD 5 FROM c;
+ four 
+------
+    3
+    2
+    1
+    0
+(4 rows)
+
+END;
diff --git a/src/test/regress/expected/sysviews.out b/src/test/regress/expected/sysviews.out
index a1c90eb905..bd3b373515 100644
--- a/src/test/regress/expected/sysviews.out
+++ b/src/test/regress/expected/sysviews.out
@@ -78,6 +78,7 @@ select name, setting from pg_settings where name like 'enable%';
  enable_hashjoin                | on
  enable_indexonlyscan           | on
  enable_indexscan               | on
+ enable_indexskipscan           | on
  enable_material                | on
  enable_mergejoin               | on
  enable_nestloop                | on
@@ -89,7 +90,7 @@ select name, setting from pg_settings where name like 'enable%';
  enable_seqscan                 | on
  enable_sort                    | on
  enable_tidscan                 | on
-(17 rows)
+(18 rows)
 
 -- Test that the pg_timezone_names and pg_timezone_abbrevs views are
 -- more-or-less working.  We can't test their contents in any great detail
diff --git a/src/test/regress/sql/create_index.sql b/src/test/regress/sql/create_index.sql
index cd46f071bd..04760639a8 100644
--- a/src/test/regress/sql/create_index.sql
+++ b/src/test/regress/sql/create_index.sql
@@ -26,6 +26,8 @@ CREATE INDEX tenk1_hundred ON tenk1 USING btree(hundred int4_ops);
 
 CREATE INDEX tenk1_thous_tenthous ON tenk1 (thousand, tenthous);
 
+CREATE INDEX tenk1_four ON tenk1 (four);
+
 CREATE INDEX tenk2_unique1 ON tenk2 USING btree(unique1 int4_ops);
 
 CREATE INDEX tenk2_unique2 ON tenk2 USING btree(unique2 int4_ops);
diff --git a/src/test/regress/sql/select_distinct.sql b/src/test/regress/sql/select_distinct.sql
index a605e86449..ab7e7bd53c 100644
--- a/src/test/regress/sql/select_distinct.sql
+++ b/src/test/regress/sql/select_distinct.sql
@@ -73,3 +73,58 @@ SELECT 1 IS NOT DISTINCT FROM 2 as "no";
 SELECT 2 IS NOT DISTINCT FROM 2 as "yes";
 SELECT 2 IS NOT DISTINCT FROM null as "no";
 SELECT null IS NOT DISTINCT FROM null as "yes";
+
+-- index skip scan
+SELECT DISTINCT four FROM tenk1;
+SELECT DISTINCT four FROM tenk1 WHERE four = 1;
+
+-- check colums order
+SELECT DISTINCT four FROM tenk1 WHERE ten = 2;
+
+CREATE INDEX tenk1_four_ten on tenk1 (four, ten);
+
+SELECT DISTINCT four FROM tenk1 WHERE ten = 2;
+SELECT DISTINCT on (four, ten) four, ten FROM tenk1 WHERE four = 0;
+
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT DISTINCT four FROM tenk1 WHERE ten = 2;
+
+-- test uniq_distinct_pathkeys
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT DISTINCT on (four, ten) four, ten FROM tenk1 WHERE four = 0;
+
+DROP INDEX tenk1_four_ten;
+
+CREATE INDEX tenk1_ten_four on tenk1 (ten, four);
+
+SELECT DISTINCT four FROM tenk1 WHERE ten = 2;
+SELECT DISTINCT on (four, ten) four, ten FROM tenk1 WHERE ten = 2;
+
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT DISTINCT four FROM tenk1 WHERE ten = 2;
+
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT DISTINCT on (four, ten) four, ten FROM tenk1 WHERE ten = 2;
+
+DROP INDEX tenk1_ten_four;
+
+-- check projection case
+SELECT DISTINCT four, four FROM tenk1 WHERE ten = 2;
+SELECT DISTINCT four, 1 FROM tenk1 WHERE ten = 2;
+
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT DISTINCT four FROM tenk1;
+
+BEGIN;
+DECLARE c SCROLL CURSOR FOR SELECT DISTINCT four FROM tenk1;
+
+FETCH FROM c;
+FETCH BACKWARD FROM c;
+
+FETCH 5 FROM c;
+FETCH BACKWARD 5 FROM c;
+
+FETCH 5 FROM c;
+FETCH BACKWARD 5 FROM c;
+
+END;
-- 
2.21.0


--------------5BA7E08BAA6962C3F49CD843--





^ permalink  raw  reply  [nested|flat] 12+ messages in thread

* [PATCH v8 1/5] Add pgstat_report_anytime_stat() for periodic stats flushing
@ 2026-01-05 09:41 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-05 09:41 UTC (permalink / raw)

Long running transactions can accumulate significant statistics (WAL, IO, ...)
that remain unflushed until the transaction ends. This delays visibility of
resource usage in monitoring views like pg_stat_io and pg_stat_wal and produces
spikes when flushed.

This commit introduces pgstat_report_anytime_stat(), which flushes
non transactional statistics even inside active transactions. A new timeout
handler fires every second (if enabled while adding pending stats) to call this
function, ensuring timely stats visibility without waiting for transaction completion.

Implementation details:

- Add PgStat_FlushMode enum to classify stats kinds:
  * FLUSH_ANYTIME: Stats that can always be flushed (WAL, IO, ...)
  * FLUSH_AT_TXN_BOUNDARY: Stats requiring transaction boundaries

- Modify pgstat_flush_pending_entries() and pgstat_flush_fixed_stats()
  to accept a boolean anytime_only parameter:
  * When false: flushes all stats (existing behavior)
  * When true: flushes only FLUSH_ANYTIME stats and skips FLUSH_AT_TXN_BOUNDARY stats

- The flush_pending_cb and flush_static_cb callbacks now receive an anytime_only
boolean parameter. Most of the time it's not used (except for assertions), but it's
preparatory work for moving the relations stats to anytime (without introducin
a new callback).

- Add pgstat_schedule_anytime_update() macro to schedule the next anytime flush,
relying on PGSTAT_MIN_INTERVAL

The force parameter in pgstat_report_anytime_stat() is currently unused (always
called with force=false) but reserved for future use cases requiring immediate
flushing.
---
 src/backend/access/transam/xlog.c             |   6 +
 src/backend/postmaster/bgwriter.c             |   9 +-
 src/backend/postmaster/checkpointer.c         |  10 +-
 src/backend/postmaster/startup.c              |   2 +
 src/backend/postmaster/walsummarizer.c        |   9 +-
 src/backend/postmaster/walwriter.c            |   9 +-
 src/backend/replication/walreceiver.c         |   9 +-
 src/backend/replication/walsender.c           |   8 +-
 src/backend/tcop/postgres.c                   |  12 ++
 src/backend/utils/activity/pgstat.c           | 112 ++++++++++++++----
 src/backend/utils/activity/pgstat_backend.c   |  13 +-
 src/backend/utils/activity/pgstat_bgwriter.c  |   2 +-
 .../utils/activity/pgstat_checkpointer.c      |   2 +-
 src/backend/utils/activity/pgstat_database.c  |   2 +-
 src/backend/utils/activity/pgstat_function.c  |   4 +-
 src/backend/utils/activity/pgstat_io.c        |  10 +-
 src/backend/utils/activity/pgstat_relation.c  |  12 +-
 src/backend/utils/activity/pgstat_slru.c      |   6 +-
 .../utils/activity/pgstat_subscription.c      |   4 +-
 src/backend/utils/activity/pgstat_wal.c       |  10 +-
 src/backend/utils/init/globals.c              |   1 +
 src/backend/utils/init/postinit.c             |   3 +
 src/include/miscadmin.h                       |   1 +
 src/include/pgstat.h                          |  16 +++
 src/include/utils/pgstat_internal.h           |  52 ++++++--
 src/include/utils/timeout.h                   |   1 +
 .../test_custom_stats/test_custom_var_stats.c |   4 +-
 src/tools/pgindent/typedefs.list              |   1 +
 28 files changed, 264 insertions(+), 66 deletions(-)
  10.8% src/backend/postmaster/
   6.0% src/backend/replication/
  50.7% src/backend/utils/activity/
   6.0% src/backend/
  19.3% src/include/utils/
   5.6% src/include/

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..d01b11c7470 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -1085,6 +1085,9 @@ XLogInsertRecord(XLogRecData *rdata,
 		pgWalUsage.wal_fpi += num_fpi;
 		pgWalUsage.wal_fpi_bytes += fpi_bytes;
 
+		/* Schedule next anytime stats update timeout */
+		pgstat_schedule_anytime_update();
+
 		/* Required for the flush of pending stats WAL data */
 		pgstat_report_fixed = true;
 	}
@@ -2066,6 +2069,9 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic)
 					pgWalUsage.wal_buffers_full++;
 					TRACE_POSTGRESQL_WAL_BUFFER_WRITE_DIRTY_DONE();
 
+					/* Schedule next anytime stats update timeout */
+					pgstat_schedule_anytime_update();
+
 					/*
 					 * Required for the flush of pending stats WAL data, per
 					 * update of pgWalUsage.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 0956bd39a85..059c601c3b8 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -49,7 +49,9 @@
 #include "storage/smgr.h"
 #include "storage/standby.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 /*
@@ -103,7 +105,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN);
@@ -113,6 +115,11 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * We just started, assume there has been either a shutdown or
 	 * end-of-recovery snapshot.
diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c
index e03c19123bc..e11c4b099c8 100644
--- a/src/backend/postmaster/checkpointer.c
+++ b/src/backend/postmaster/checkpointer.c
@@ -66,8 +66,9 @@
 #include "utils/acl.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
-
+#include "utils/timeout.h"
 
 /*----------
  * Shared memory area for communication between checkpointer and backends
@@ -215,7 +216,7 @@ CheckpointerMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, ReqShutdownXLOG);
 	pqsignal(SIGTERM, SIG_IGN); /* ignore SIGTERM */
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SignalHandlerForShutdownRequest);
@@ -225,6 +226,11 @@ CheckpointerMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * Initialize so that first time-driven event happens at the correct time.
 	 */
diff --git a/src/backend/postmaster/startup.c b/src/backend/postmaster/startup.c
index cdbe53dd262..4954fe425b7 100644
--- a/src/backend/postmaster/startup.c
+++ b/src/backend/postmaster/startup.c
@@ -32,6 +32,7 @@
 #include "storage/standby.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timeout.h"
 
 
@@ -245,6 +246,7 @@ StartupProcessMain(const void *startup_data, size_t startup_data_len)
 	RegisterTimeout(STANDBY_DEADLOCK_TIMEOUT, StandbyDeadLockHandler);
 	RegisterTimeout(STANDBY_TIMEOUT, StandbyTimeoutHandler);
 	RegisterTimeout(STANDBY_LOCK_TIMEOUT, StandbyLockTimeoutHandler);
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
 
 	/*
 	 * Unblock signals (they were blocked when the postmaster forked us)
diff --git a/src/backend/postmaster/walsummarizer.c b/src/backend/postmaster/walsummarizer.c
index 742137edad6..f1bae9d23d6 100644
--- a/src/backend/postmaster/walsummarizer.c
+++ b/src/backend/postmaster/walsummarizer.c
@@ -48,6 +48,8 @@
 #include "storage/shmem.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 #include "utils/wait_event.h"
 
 /*
@@ -246,7 +248,7 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);	/* no query to cancel */
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN); /* not used */
@@ -268,6 +270,11 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * If an exception is encountered, processing resumes here.
 	 */
diff --git a/src/backend/postmaster/walwriter.c b/src/backend/postmaster/walwriter.c
index 7c0e2809c17..bcf59227a00 100644
--- a/src/backend/postmaster/walwriter.c
+++ b/src/backend/postmaster/walwriter.c
@@ -61,7 +61,9 @@
 #include "storage/smgr.h"
 #include "utils/hsearch.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
+#include "utils/timeout.h"
 
 
 /*
@@ -103,7 +105,7 @@ WalWriterMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);	/* no query to cancel */
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN); /* not used */
@@ -113,6 +115,11 @@ WalWriterMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * Create a memory context that we will do all our work in.  We do this so
 	 * that we can reset the context during error recovery and thereby avoid
diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index 10e64a7d1f4..11b7c114d3b 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -77,7 +77,9 @@
 #include "utils/builtins.h"
 #include "utils/guc.h"
 #include "utils/pg_lsn.h"
+#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 
@@ -252,7 +254,7 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);
 	pqsignal(SIGTERM, die);		/* request shutdown */
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN);
@@ -260,6 +262,11 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/* Load the libpq-specific functions */
 	load_file("libpqwalreceiver", false);
 	if (WalReceiverFunctions == NULL)
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 2cde8ebc729..a7214d0dc6f 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -1987,8 +1987,8 @@ WalSndWaitForWal(XLogRecPtr loc)
 		if (TimestampDifferenceExceeds(last_flush, now,
 									   WALSENDER_STATS_FLUSH_INTERVAL))
 		{
-			pgstat_flush_io(false);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+			pgstat_flush_io(false, true);
+			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 			last_flush = now;
 		}
 
@@ -3016,8 +3016,8 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			if (TimestampDifferenceExceeds(last_flush, now,
 										   WALSENDER_STATS_FLUSH_INTERVAL))
 			{
-				pgstat_flush_io(false);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+				pgstat_flush_io(false, true);
+				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 				last_flush = now;
 			}
 
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index 21de158adbb..2089de782d5 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -3564,6 +3564,18 @@ ProcessInterrupts(void)
 		pgstat_report_stat(true);
 	}
 
+	/*
+	 * Flush stats outside of transaction boundary if the timeout fired.
+	 * Unlike transactional stats, these can be flushed even inside a running
+	 * transaction.
+	 */
+	if (AnytimeStatsUpdateTimeoutPending)
+	{
+		AnytimeStatsUpdateTimeoutPending = false;
+
+		pgstat_report_anytime_stat(false);
+	}
+
 	if (ProcSignalBarrierPending)
 		ProcessProcSignalBarrier();
 
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 11bb71cad5a..a4ff64dc5ce 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -112,6 +112,7 @@
 #include "utils/guc_hooks.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 
@@ -122,8 +123,6 @@
  * ----------
  */
 
-/* minimum interval non-forced stats flushes.*/
-#define PGSTAT_MIN_INTERVAL			1000
 /* how long until to block flushing pending stats updates */
 #define PGSTAT_MAX_INTERVAL			60000
 /* when to call pgstat_report_stat() again, even when idle */
@@ -187,7 +186,8 @@ static void pgstat_init_snapshot_fixed(void);
 
 static void pgstat_reset_after_failure(void);
 
-static bool pgstat_flush_pending_entries(bool nowait);
+static bool pgstat_flush_pending_entries(bool nowait, bool anytime_only);
+static bool pgstat_flush_fixed_stats(bool nowait, bool anytime_only);
 
 static void pgstat_prep_snapshot(void);
 static void pgstat_build_snapshot(void);
@@ -288,6 +288,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_database entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -305,6 +306,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Relation),
 		.shared_data_off = offsetof(PgStatShared_Relation, stats),
@@ -321,6 +323,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Function),
 		.shared_data_off = offsetof(PgStatShared_Function, stats),
@@ -336,6 +339,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.accessed_across_databases = true,
 
@@ -353,6 +357,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_subscription_stats entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -370,6 +375,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = false,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.accessed_across_databases = true,
 
@@ -436,6 +442,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
@@ -453,6 +460,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, slru),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, slru),
@@ -470,6 +478,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, wal),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, wal),
@@ -775,23 +784,11 @@ pgstat_report_stat(bool force)
 	partial_flush = false;
 
 	/* flush of variable-numbered stats tracked in pending entries list */
-	partial_flush |= pgstat_flush_pending_entries(nowait);
+	partial_flush |= pgstat_flush_pending_entries(nowait, false);
 
 	/* flush of other stats kinds */
 	if (pgstat_report_fixed)
-	{
-		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;
-
-			partial_flush |= kind_info->flush_static_cb(nowait);
-		}
-	}
+		partial_flush |= pgstat_flush_fixed_stats(nowait, false);
 
 	last_flush = now;
 
@@ -1293,7 +1290,8 @@ pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid, uint64 objid, bool *creat
 
 	if (entry_ref->pending == NULL)
 	{
-		size_t		entrysize = pgstat_get_kind_info(kind)->pending_size;
+		const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
+		size_t		entrysize = kind_info->pending_size;
 
 		Assert(entrysize != (size_t) -1);
 
@@ -1345,9 +1343,14 @@ pgstat_delete_pending_entry(PgStat_EntryRef *entry_ref)
 
 /*
  * Flush out pending variable-numbered stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME entries.
+ * This is safe to call inside transactions.
+ *
+ * If anytime_only is false, flushes all entries.
  */
 static bool
-pgstat_flush_pending_entries(bool nowait)
+pgstat_flush_pending_entries(bool nowait, bool anytime_only)
 {
 	bool		have_pending = false;
 	dlist_node *cur = NULL;
@@ -1377,8 +1380,22 @@ pgstat_flush_pending_entries(bool nowait)
 		Assert(!kind_info->fixed_amount);
 		Assert(kind_info->flush_pending_cb != NULL);
 
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+		{
+			have_pending = true;
+
+			if (dlist_has_next(&pgStatPending, cur))
+				next = dlist_next_node(&pgStatPending, cur);
+			else
+				next = NULL;
+
+			cur = next;
+			continue;
+		}
+
 		/* flush the stats, if possible */
-		did_flush = kind_info->flush_pending_cb(entry_ref, nowait);
+		did_flush = kind_info->flush_pending_cb(entry_ref, nowait, anytime_only);
 
 		Assert(did_flush || nowait);
 
@@ -1402,6 +1419,33 @@ pgstat_flush_pending_entries(bool nowait)
 	return have_pending;
 }
 
+/*
+ * Flush fixed-amount stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME stats (safe inside transactions).
+ * If anytime_only is false, flushes all stats with flush_static_cb.
+ */
+static bool
+pgstat_flush_fixed_stats(bool nowait, bool anytime_only)
+{
+	bool		partial_flush = false;
+
+	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 || !kind_info->flush_static_cb)
+			continue;
+
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+			continue;
+
+		partial_flush |= kind_info->flush_static_cb(nowait, anytime_only);
+	}
+
+	return partial_flush;
+}
 
 /* ------------------------------------------------------------
  * Helper / infrastructure functions
@@ -2119,3 +2163,31 @@ assign_stats_fetch_consistency(int newval, void *extra)
 	if (pgstat_fetch_consistency != newval)
 		force_stats_snapshot_clear = true;
 }
+
+/*
+ * Flushes only FLUSH_ANYTIME stats using non-blocking locks. Transactional
+ * stats (FLUSH_AT_TXN_BOUNDARY) remain pending until transaction boundary.
+ * Safe to call inside transactions.
+ */
+void
+pgstat_report_anytime_stat(bool force)
+{
+	bool		nowait = !force;
+
+	pgstat_assert_is_up();
+
+	/* Flush stats outside of transaction boundary */
+	pgstat_flush_pending_entries(nowait, true);
+	pgstat_flush_fixed_stats(nowait, true);
+}
+
+/*
+ * Timeout handler for flushing anytime stats.
+ */
+void
+AnytimeStatsUpdateTimeoutHandler(void)
+{
+	AnytimeStatsUpdateTimeoutPending = true;
+	InterruptPending = true;
+	SetLatch(MyLatch);
+}
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index f2f8d3ff75f..b09316d3ab3 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -31,6 +31,7 @@
 #include "storage/procarray.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 
 /*
  * Backend statistics counts waiting to be flushed out. These counters may be
@@ -66,6 +67,9 @@ pgstat_count_backend_io_op_time(IOObject io_object, IOContext io_context,
 	INSTR_TIME_ADD(PendingBackendStats.pending_io.pending_times[io_object][io_context][io_op],
 				   io_time);
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	backend_has_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -82,6 +86,9 @@ pgstat_count_backend_io_op(IOObject io_object, IOContext io_context,
 	PendingBackendStats.pending_io.counts[io_object][io_context][io_op] += cnt;
 	PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	backend_has_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -268,7 +275,7 @@ pgstat_flush_backend_entry_wal(PgStat_EntryRef *entry_ref)
  * if some statistics could not be flushed due to lock contention.
  */
 bool
-pgstat_flush_backend(bool nowait, bits32 flags)
+pgstat_flush_backend(bool nowait, bits32 flags, bool anytime_only)
 {
 	PgStat_EntryRef *entry_ref;
 	bool		has_pending_data = false;
@@ -311,9 +318,9 @@ pgstat_flush_backend(bool nowait, bits32 flags)
  * If some stats could not be flushed due to lock contention, return true.
  */
 bool
-pgstat_backend_flush_cb(bool nowait)
+pgstat_backend_flush_cb(bool nowait, bool anytime_only)
 {
-	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL);
+	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL, anytime_only);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_bgwriter.c b/src/backend/utils/activity/pgstat_bgwriter.c
index ed2fd801189..1c5f0c3ec40 100644
--- a/src/backend/utils/activity/pgstat_bgwriter.c
+++ b/src/backend/utils/activity/pgstat_bgwriter.c
@@ -61,7 +61,7 @@ pgstat_report_bgwriter(void)
 	/*
 	 * Report IO statistics
 	 */
-	pgstat_flush_io(false);
+	pgstat_flush_io(false, true);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_checkpointer.c b/src/backend/utils/activity/pgstat_checkpointer.c
index 1f70194b7a7..2d89a082464 100644
--- a/src/backend/utils/activity/pgstat_checkpointer.c
+++ b/src/backend/utils/activity/pgstat_checkpointer.c
@@ -68,7 +68,7 @@ pgstat_report_checkpointer(void)
 	/*
 	 * Report IO statistics
 	 */
-	pgstat_flush_io(false);
+	pgstat_flush_io(false, true);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_database.c b/src/backend/utils/activity/pgstat_database.c
index 933dcb5cae5..8e86df60461 100644
--- a/src/backend/utils/activity/pgstat_database.c
+++ b/src/backend/utils/activity/pgstat_database.c
@@ -435,7 +435,7 @@ pgstat_reset_database_timestamp(Oid dboid, TimestampTz ts)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStatShared_Database *sharedent;
 	PgStat_StatDBEntry *pendingent;
diff --git a/src/backend/utils/activity/pgstat_function.c b/src/backend/utils/activity/pgstat_function.c
index e6b84283c6c..5ba4958382f 100644
--- a/src/backend/utils/activity/pgstat_function.c
+++ b/src/backend/utils/activity/pgstat_function.c
@@ -190,11 +190,13 @@ pgstat_end_function_usage(PgStat_FunctionCallUsage *fcu, bool finalize)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_FunctionCounts *localent;
 	PgStatShared_Function *shfuncent;
 
+	Assert(!anytime_only);
+
 	localent = (PgStat_FunctionCounts *) entry_ref->pending;
 	shfuncent = (PgStatShared_Function *) entry_ref->shared_stats;
 
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 28de24538dc..7cd32900236 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -19,6 +19,7 @@
 #include "executor/instrument.h"
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
@@ -79,6 +80,9 @@ pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op,
 	/* Add the per-backend counts */
 	pgstat_count_backend_io_op(io_object, io_context, io_op, cnt, bytes);
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	have_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -172,9 +176,9 @@ pgstat_fetch_stat_io(void)
  * Simpler wrapper of pgstat_io_flush_cb()
  */
 void
-pgstat_flush_io(bool nowait)
+pgstat_flush_io(bool nowait, bool anytime_only)
 {
-	(void) pgstat_io_flush_cb(nowait);
+	(void) pgstat_io_flush_cb(nowait, anytime_only);
 }
 
 /*
@@ -186,7 +190,7 @@ pgstat_flush_io(bool nowait)
  * acquired. Otherwise, return false.
  */
 bool
-pgstat_io_flush_cb(bool nowait)
+pgstat_io_flush_cb(bool nowait, bool anytime_only)
 {
 	LWLock	   *bktype_lock;
 	PgStat_BktypeIO *bktype_shstats;
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..04d21483d93 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -267,8 +267,8 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	 * is done -- which will likely vacuum many relations -- or until the
 	 * VACUUM command has processed all tables and committed.
 	 */
-	pgstat_flush_io(false);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(false, true);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -362,8 +362,8 @@ pgstat_report_analyze(Relation rel,
 	pgstat_unlock_entry(entry_ref);
 
 	/* see pgstat_report_vacuum() */
-	pgstat_flush_io(false);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(false, true);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -812,7 +812,7 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
  * entry when successfully flushing.
  */
 bool
-pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	Oid			dboid;
 	PgStat_TableStatus *lstats; /* pending stats entry  */
@@ -820,6 +820,8 @@ pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
 	PgStat_StatTabEntry *tabentry;	/* table entry of shared stats */
 	PgStat_StatDBEntry *dbentry;	/* pending database entry */
 
+	Assert(!anytime_only);
+
 	dboid = entry_ref->shared_entry->key.dboid;
 	lstats = (PgStat_TableStatus *) entry_ref->pending;
 	shtabstats = (PgStatShared_Relation *) entry_ref->shared_stats;
diff --git a/src/backend/utils/activity/pgstat_slru.c b/src/backend/utils/activity/pgstat_slru.c
index 2190f388eae..bf8a4d58673 100644
--- a/src/backend/utils/activity/pgstat_slru.c
+++ b/src/backend/utils/activity/pgstat_slru.c
@@ -19,6 +19,7 @@
 
 #include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
+#include "utils/timeout.h"
 
 
 static inline PgStat_SLRUStats *get_slru_entry(int slru_idx);
@@ -139,7 +140,7 @@ pgstat_get_slru_index(const char *name)
  * acquired. Otherwise return false.
  */
 bool
-pgstat_slru_flush_cb(bool nowait)
+pgstat_slru_flush_cb(bool nowait, bool anytime_only)
 {
 	PgStatShared_SLRU *stats_shmem = &pgStatLocal.shmem->slru;
 	int			i;
@@ -223,6 +224,9 @@ get_slru_entry(int slru_idx)
 
 	Assert((slru_idx >= 0) && (slru_idx < SLRU_NUM_ELEMENTS));
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	have_slrustats = true;
 	pgstat_report_fixed = true;
 
diff --git a/src/backend/utils/activity/pgstat_subscription.c b/src/backend/utils/activity/pgstat_subscription.c
index 500b1899188..c4614817966 100644
--- a/src/backend/utils/activity/pgstat_subscription.c
+++ b/src/backend/utils/activity/pgstat_subscription.c
@@ -116,11 +116,13 @@ pgstat_fetch_stat_subscription(Oid subid)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_BackendSubEntry *localent;
 	PgStatShared_Subscription *shsubent;
 
+	Assert(!anytime_only);
+
 	localent = (PgStat_BackendSubEntry *) entry_ref->pending;
 	shsubent = (PgStatShared_Subscription *) entry_ref->shared_stats;
 
diff --git a/src/backend/utils/activity/pgstat_wal.c b/src/backend/utils/activity/pgstat_wal.c
index 183e0a7a97b..2c2f3f10e10 100644
--- a/src/backend/utils/activity/pgstat_wal.c
+++ b/src/backend/utils/activity/pgstat_wal.c
@@ -51,12 +51,12 @@ pgstat_report_wal(bool force)
 	nowait = !force;
 
 	/* flush wal stats */
-	(void) pgstat_wal_flush_cb(nowait);
-	pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_WAL);
+	(void) pgstat_wal_flush_cb(nowait, true);
+	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_WAL, true);
 
 	/* flush IO stats */
-	pgstat_flush_io(nowait);
-	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(nowait, true);
+	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -88,7 +88,7 @@ pgstat_wal_have_pending(void)
  * acquired. Otherwise return false.
  */
 bool
-pgstat_wal_flush_cb(bool nowait)
+pgstat_wal_flush_cb(bool nowait, bool anytime_only)
 {
 	PgStatShared_Wal *stats_shmem = &pgStatLocal.shmem->wal;
 	WalUsage	wal_usage_diff = {0};
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 36ad708b360..ad44826c39e 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -40,6 +40,7 @@ volatile sig_atomic_t IdleSessionTimeoutPending = false;
 volatile sig_atomic_t ProcSignalBarrierPending = false;
 volatile sig_atomic_t LogMemoryContextPending = false;
 volatile sig_atomic_t IdleStatsUpdateTimeoutPending = false;
+volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending = false;
 volatile uint32 InterruptHoldoffCount = 0;
 volatile uint32 QueryCancelHoldoffCount = 0;
 volatile uint32 CritSectionCount = 0;
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index b59e08605cc..eeeac1bf39a 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -64,6 +64,7 @@
 #include "utils/injection_point.h"
 #include "utils/memutils.h"
 #include "utils/pg_locale.h"
+#include "utils/pgstat_internal.h"
 #include "utils/portal.h"
 #include "utils/ps_status.h"
 #include "utils/snapmgr.h"
@@ -773,6 +774,8 @@ InitPostgres(const char *in_dbname, Oid dboid,
 		RegisterTimeout(CLIENT_CONNECTION_CHECK_TIMEOUT, ClientCheckTimeoutHandler);
 		RegisterTimeout(IDLE_STATS_UPDATE_TIMEOUT,
 						IdleStatsUpdateTimeoutHandler);
+		RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT,
+						AnytimeStatsUpdateTimeoutHandler);
 	}
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index f16f35659b9..84e698da214 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -96,6 +96,7 @@ extern PGDLLIMPORT volatile sig_atomic_t IdleSessionTimeoutPending;
 extern PGDLLIMPORT volatile sig_atomic_t ProcSignalBarrierPending;
 extern PGDLLIMPORT volatile sig_atomic_t LogMemoryContextPending;
 extern PGDLLIMPORT volatile sig_atomic_t IdleStatsUpdateTimeoutPending;
+extern PGDLLIMPORT volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending;
 
 extern PGDLLIMPORT volatile sig_atomic_t CheckClientConnectionPending;
 extern PGDLLIMPORT volatile sig_atomic_t ClientConnectionLost;
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index fff7ecc2533..b340a680614 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -35,6 +35,9 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/* Minimum interval non-forced stats flushes */
+#define PGSTAT_MIN_INTERVAL	1000
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -533,8 +536,21 @@ extern void pgstat_initialize(void);
 
 /* Functions called from backends */
 extern long pgstat_report_stat(bool force);
+extern void pgstat_report_anytime_stat(bool force);
 extern void pgstat_force_next_flush(void);
 
+/*
+ * Schedule the next anytime stats update timeout.
+ *
+ * This should be called whenever accumulating statistics that support
+ * FLUSH_ANYTIME flushing mode.
+ */
+#define pgstat_schedule_anytime_update()												\
+	do {																				\
+		if (IsUnderPostmaster && !get_timeout_active(ANYTIME_STATS_UPDATE_TIMEOUT))		\
+			enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);	\
+	} while (0)
+
 extern void pgstat_reset_counters(void);
 extern void pgstat_reset(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_reset_of_kind(PgStat_Kind kind);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..607f4255268 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -224,6 +224,19 @@ typedef struct PgStat_SubXactStatus
 	PgStat_TableXactStatus *first;	/* head of list for this subxact */
 } PgStat_SubXactStatus;
 
+/*
+ * Flush mode for statistics kinds.
+ *
+ * FLUSH_AT_TXN_BOUNDARY has to be the first because we want it to be the
+ * default value.
+ */
+typedef enum PgStat_FlushMode
+{
+	FLUSH_AT_TXN_BOUNDARY,		/* All fields can only be flushed at
+								 * transaction boundary */
+	FLUSH_ANYTIME,				/* All fields can be flushed anytime,
+								 * including within transactions */
+} PgStat_FlushMode;
 
 /*
  * Metadata for a specific kind of statistics.
@@ -251,6 +264,16 @@ typedef struct PgStat_KindInfo
 	 */
 	bool		track_entry_count:1;
 
+	/*
+	 * The mode of when to flush stats. See PgStat_FlushMode for more details.
+	 *
+	 * This member only has meaning for statistics kinds that accumulate
+	 * pending stats and use flush callbacks. For kinds that write directly to
+	 * shared memory (e.g., archiver, bgwriter, checkpointer), this member has
+	 * no effect.
+	 */
+	PgStat_FlushMode flush_mode;
+
 	/*
 	 * The size of an entry in the shared stats hash table (pointed to by
 	 * PgStatShared_HashEntry->body).  For fixed-numbered statistics, this is
@@ -297,8 +320,10 @@ typedef struct PgStat_KindInfo
 	 * For variable-numbered stats: flush pending stats. Required if pending
 	 * data is used. See flush_static_cb when dealing with stats data that
 	 * that cannot use PgStat_EntryRef->pending.
+	 *
+	 * The anytime_only parameter indicates whether this is an anytime flush.
 	 */
-	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait);
+	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait, bool anytime_only);
 
 	/*
 	 * For variable-numbered stats: delete pending stats. Optional.
@@ -366,8 +391,10 @@ typedef struct PgStat_KindInfo
 	 *
 	 * "pgstat_report_fixed" needs to be set to trigger the flush of pending
 	 * stats.
+	 *
+	 * The anytime_only parameter indicates whether this is an anytime flush.
 	 */
-	bool		(*flush_static_cb) (bool nowait);
+	bool		(*flush_static_cb) (bool nowait, bool anytime_only);
 
 	/*
 	 * For fixed-numbered statistics: Reset All.
@@ -677,6 +704,7 @@ extern PgStat_EntryRef *pgstat_fetch_pending_entry(PgStat_Kind kind,
 
 extern void *pgstat_fetch_entry(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_snapshot_fixed(PgStat_Kind kind);
+extern void AnytimeStatsUpdateTimeoutHandler(void);
 
 
 /*
@@ -696,8 +724,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL)
 
-extern bool pgstat_flush_backend(bool nowait, bits32 flags);
-extern bool pgstat_backend_flush_cb(bool nowait);
+extern bool pgstat_flush_backend(bool nowait, bits32 flags, bool anytime_only);
+extern bool pgstat_backend_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header,
 											  TimestampTz ts);
 
@@ -729,7 +757,7 @@ extern void AtEOXact_PgStat_Database(bool isCommit, bool parallel);
 
 extern PgStat_StatDBEntry *pgstat_prep_database_pending(Oid dboid);
 extern void pgstat_reset_database_timestamp(Oid dboid, TimestampTz ts);
-extern bool pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_database_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
@@ -737,7 +765,7 @@ extern void pgstat_database_reset_timestamp_cb(PgStatShared_Common *header, Time
  * Functions in pgstat_function.c
  */
 
-extern bool pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_function_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
@@ -745,9 +773,9 @@ extern void pgstat_function_reset_timestamp_cb(PgStatShared_Common *header, Time
  * Functions in pgstat_io.c
  */
 
-extern void pgstat_flush_io(bool nowait);
+extern void pgstat_flush_io(bool nowait, bool anytime_only);
 
-extern bool pgstat_io_flush_cb(bool nowait);
+extern bool pgstat_io_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_io_init_shmem_cb(void *stats);
 extern void pgstat_io_reset_all_cb(TimestampTz ts);
 extern void pgstat_io_snapshot_cb(void);
@@ -762,7 +790,7 @@ extern void AtEOSubXact_PgStat_Relations(PgStat_SubXactStatus *xact_state, bool
 extern void AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 
-extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
@@ -809,7 +837,7 @@ extern PgStatShared_Common *pgstat_init_entry(PgStat_Kind kind,
  * Functions in pgstat_slru.c
  */
 
-extern bool pgstat_slru_flush_cb(bool nowait);
+extern bool pgstat_slru_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_slru_init_shmem_cb(void *stats);
 extern void pgstat_slru_reset_all_cb(TimestampTz ts);
 extern void pgstat_slru_snapshot_cb(void);
@@ -820,7 +848,7 @@ extern void pgstat_slru_snapshot_cb(void);
  */
 
 extern void pgstat_wal_init_backend_cb(void);
-extern bool pgstat_wal_flush_cb(bool nowait);
+extern bool pgstat_wal_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_wal_init_shmem_cb(void *stats);
 extern void pgstat_wal_reset_all_cb(TimestampTz ts);
 extern void pgstat_wal_snapshot_cb(void);
@@ -830,7 +858,7 @@ extern void pgstat_wal_snapshot_cb(void);
  * Functions in pgstat_subscription.c
  */
 
-extern bool pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_subscription_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h
index 0965b590b34..10723bb664c 100644
--- a/src/include/utils/timeout.h
+++ b/src/include/utils/timeout.h
@@ -35,6 +35,7 @@ typedef enum TimeoutId
 	IDLE_SESSION_TIMEOUT,
 	IDLE_STATS_UPDATE_TIMEOUT,
 	CLIENT_CONNECTION_CHECK_TIMEOUT,
+	ANYTIME_STATS_UPDATE_TIMEOUT,
 	STARTUP_PROGRESS_TIMEOUT,
 	/* First user-definable timeout reason */
 	USER_TIMEOUT,
diff --git a/src/test/modules/test_custom_stats/test_custom_var_stats.c b/src/test/modules/test_custom_stats/test_custom_var_stats.c
index 64a8fe63cce..bc0b5d6e0eb 100644
--- a/src/test/modules/test_custom_stats/test_custom_var_stats.c
+++ b/src/test/modules/test_custom_stats/test_custom_var_stats.c
@@ -83,7 +83,7 @@ static dsa_area *custom_stats_description_dsa = NULL;
 
 /* Flush callback: merge pending stats into shared memory */
 static bool test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref,
-												   bool nowait);
+												   bool nowait, bool anytime_only);
 
 /* Serialization callback: write auxiliary entry data */
 static void test_custom_stats_var_to_serialized_data(const PgStat_HashKey *key,
@@ -150,7 +150,7 @@ _PG_init(void)
  * Returns false only if nowait=true and lock acquisition fails.
  */
 static bool
-test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref, bool nowait)
+test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_StatCustomVarEntry *pending_entry;
 	PgStatShared_CustomVarEntry *shared_entry;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 241945734ec..1dbc4b96f51 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2271,6 +2271,7 @@ PgStat_Counter
 PgStat_EntryRef
 PgStat_EntryRefHashEntry
 PgStat_FetchConsistency
+PgStat_FlushMode
 PgStat_FunctionCallUsage
 PgStat_FunctionCounts
 PgStat_HashKey
-- 
2.34.1


--OI5irqZsxWxBW9nT
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v8-0002-Add-anytime-flush-tests-for-custom-stats.patch"



^ permalink  raw  reply  [nested|flat] 12+ messages in thread

* [PATCH v9 1/5] Add pgstat_report_anytime_stat() for periodic stats flushing
@ 2026-01-05 09:41 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-05 09:41 UTC (permalink / raw)

Long running transactions can accumulate significant statistics (WAL, IO, ...)
that remain unflushed until the transaction ends. This delays visibility of
resource usage in monitoring views like pg_stat_io and pg_stat_wal and produces
spikes when flushed.

This commit introduces pgstat_report_anytime_stat(), which flushes
non transactional statistics even inside active transactions. A new timeout
handler fires every second (if enabled while adding pending stats) to call this
function, ensuring timely stats visibility without waiting for transaction completion.

Implementation details:

- Add PgStat_FlushMode enum to classify stats kinds:
  * FLUSH_ANYTIME: Stats that can always be flushed (WAL, IO, ...)
  * FLUSH_AT_TXN_BOUNDARY: Stats requiring transaction boundaries

- Modify pgstat_flush_pending_entries() and pgstat_flush_fixed_stats()
  to accept a boolean anytime_only parameter:
  * When false: flushes all stats (existing behavior)
  * When true: flushes only FLUSH_ANYTIME stats and skips FLUSH_AT_TXN_BOUNDARY stats

- The flush_pending_cb and flush_static_cb callbacks now receive an anytime_only
boolean parameter. Most of the time it's not used (except for assertions), but it's
preparatory work for moving the relations stats to anytime (without introducin
a new callback).

- Add pgstat_schedule_anytime_update() macro to schedule the next anytime flush,
relying on PGSTAT_MIN_INTERVAL

The force parameter in pgstat_report_anytime_stat() is currently unused (always
called with force=false) but reserved for future use cases requiring immediate
flushing.
---
 src/backend/access/transam/xlog.c             |   6 +
 src/backend/postmaster/bgwriter.c             |   9 +-
 src/backend/postmaster/checkpointer.c         |  10 +-
 src/backend/postmaster/startup.c              |   2 +
 src/backend/postmaster/walsummarizer.c        |   9 +-
 src/backend/postmaster/walwriter.c            |   9 +-
 src/backend/replication/walreceiver.c         |   9 +-
 src/backend/replication/walsender.c           |   8 +-
 src/backend/tcop/postgres.c                   |  12 ++
 src/backend/utils/activity/pgstat.c           | 120 +++++++++++++++---
 src/backend/utils/activity/pgstat_backend.c   |  13 +-
 src/backend/utils/activity/pgstat_bgwriter.c  |   2 +-
 .../utils/activity/pgstat_checkpointer.c      |   2 +-
 src/backend/utils/activity/pgstat_database.c  |   2 +-
 src/backend/utils/activity/pgstat_function.c  |   4 +-
 src/backend/utils/activity/pgstat_io.c        |  10 +-
 src/backend/utils/activity/pgstat_relation.c  |  12 +-
 src/backend/utils/activity/pgstat_slru.c      |   6 +-
 .../utils/activity/pgstat_subscription.c      |   4 +-
 src/backend/utils/activity/pgstat_wal.c       |  10 +-
 src/backend/utils/init/globals.c              |   1 +
 src/backend/utils/init/postinit.c             |   3 +
 src/include/miscadmin.h                       |   1 +
 src/include/pgstat.h                          |  22 ++++
 src/include/utils/pgstat_internal.h           |  52 ++++++--
 src/include/utils/timeout.h                   |   1 +
 .../test_custom_stats/test_custom_var_stats.c |   4 +-
 src/tools/pgindent/typedefs.list              |   1 +
 28 files changed, 278 insertions(+), 66 deletions(-)
  10.5% src/backend/postmaster/
   5.8% src/backend/replication/
  50.9% src/backend/utils/activity/
   5.9% src/backend/
  18.8% src/include/utils/
   6.6% src/include/

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..d01b11c7470 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -1085,6 +1085,9 @@ XLogInsertRecord(XLogRecData *rdata,
 		pgWalUsage.wal_fpi += num_fpi;
 		pgWalUsage.wal_fpi_bytes += fpi_bytes;
 
+		/* Schedule next anytime stats update timeout */
+		pgstat_schedule_anytime_update();
+
 		/* Required for the flush of pending stats WAL data */
 		pgstat_report_fixed = true;
 	}
@@ -2066,6 +2069,9 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic)
 					pgWalUsage.wal_buffers_full++;
 					TRACE_POSTGRESQL_WAL_BUFFER_WRITE_DIRTY_DONE();
 
+					/* Schedule next anytime stats update timeout */
+					pgstat_schedule_anytime_update();
+
 					/*
 					 * Required for the flush of pending stats WAL data, per
 					 * update of pgWalUsage.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 0956bd39a85..059c601c3b8 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -49,7 +49,9 @@
 #include "storage/smgr.h"
 #include "storage/standby.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 /*
@@ -103,7 +105,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN);
@@ -113,6 +115,11 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * We just started, assume there has been either a shutdown or
 	 * end-of-recovery snapshot.
diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c
index e03c19123bc..e11c4b099c8 100644
--- a/src/backend/postmaster/checkpointer.c
+++ b/src/backend/postmaster/checkpointer.c
@@ -66,8 +66,9 @@
 #include "utils/acl.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
-
+#include "utils/timeout.h"
 
 /*----------
  * Shared memory area for communication between checkpointer and backends
@@ -215,7 +216,7 @@ CheckpointerMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, ReqShutdownXLOG);
 	pqsignal(SIGTERM, SIG_IGN); /* ignore SIGTERM */
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SignalHandlerForShutdownRequest);
@@ -225,6 +226,11 @@ CheckpointerMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * Initialize so that first time-driven event happens at the correct time.
 	 */
diff --git a/src/backend/postmaster/startup.c b/src/backend/postmaster/startup.c
index cdbe53dd262..4954fe425b7 100644
--- a/src/backend/postmaster/startup.c
+++ b/src/backend/postmaster/startup.c
@@ -32,6 +32,7 @@
 #include "storage/standby.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timeout.h"
 
 
@@ -245,6 +246,7 @@ StartupProcessMain(const void *startup_data, size_t startup_data_len)
 	RegisterTimeout(STANDBY_DEADLOCK_TIMEOUT, StandbyDeadLockHandler);
 	RegisterTimeout(STANDBY_TIMEOUT, StandbyTimeoutHandler);
 	RegisterTimeout(STANDBY_LOCK_TIMEOUT, StandbyLockTimeoutHandler);
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
 
 	/*
 	 * Unblock signals (they were blocked when the postmaster forked us)
diff --git a/src/backend/postmaster/walsummarizer.c b/src/backend/postmaster/walsummarizer.c
index 742137edad6..f1bae9d23d6 100644
--- a/src/backend/postmaster/walsummarizer.c
+++ b/src/backend/postmaster/walsummarizer.c
@@ -48,6 +48,8 @@
 #include "storage/shmem.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 #include "utils/wait_event.h"
 
 /*
@@ -246,7 +248,7 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);	/* no query to cancel */
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN); /* not used */
@@ -268,6 +270,11 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * If an exception is encountered, processing resumes here.
 	 */
diff --git a/src/backend/postmaster/walwriter.c b/src/backend/postmaster/walwriter.c
index 7c0e2809c17..bcf59227a00 100644
--- a/src/backend/postmaster/walwriter.c
+++ b/src/backend/postmaster/walwriter.c
@@ -61,7 +61,9 @@
 #include "storage/smgr.h"
 #include "utils/hsearch.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
+#include "utils/timeout.h"
 
 
 /*
@@ -103,7 +105,7 @@ WalWriterMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);	/* no query to cancel */
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN); /* not used */
@@ -113,6 +115,11 @@ WalWriterMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * Create a memory context that we will do all our work in.  We do this so
 	 * that we can reset the context during error recovery and thereby avoid
diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index 10e64a7d1f4..11b7c114d3b 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -77,7 +77,9 @@
 #include "utils/builtins.h"
 #include "utils/guc.h"
 #include "utils/pg_lsn.h"
+#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 
@@ -252,7 +254,7 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);
 	pqsignal(SIGTERM, die);		/* request shutdown */
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN);
@@ -260,6 +262,11 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/* Load the libpq-specific functions */
 	load_file("libpqwalreceiver", false);
 	if (WalReceiverFunctions == NULL)
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 2cde8ebc729..a7214d0dc6f 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -1987,8 +1987,8 @@ WalSndWaitForWal(XLogRecPtr loc)
 		if (TimestampDifferenceExceeds(last_flush, now,
 									   WALSENDER_STATS_FLUSH_INTERVAL))
 		{
-			pgstat_flush_io(false);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+			pgstat_flush_io(false, true);
+			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 			last_flush = now;
 		}
 
@@ -3016,8 +3016,8 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			if (TimestampDifferenceExceeds(last_flush, now,
 										   WALSENDER_STATS_FLUSH_INTERVAL))
 			{
-				pgstat_flush_io(false);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+				pgstat_flush_io(false, true);
+				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 				last_flush = now;
 			}
 
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index 21de158adbb..2089de782d5 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -3564,6 +3564,18 @@ ProcessInterrupts(void)
 		pgstat_report_stat(true);
 	}
 
+	/*
+	 * Flush stats outside of transaction boundary if the timeout fired.
+	 * Unlike transactional stats, these can be flushed even inside a running
+	 * transaction.
+	 */
+	if (AnytimeStatsUpdateTimeoutPending)
+	{
+		AnytimeStatsUpdateTimeoutPending = false;
+
+		pgstat_report_anytime_stat(false);
+	}
+
 	if (ProcSignalBarrierPending)
 		ProcessProcSignalBarrier();
 
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 11bb71cad5a..419dc512d9b 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -112,6 +112,7 @@
 #include "utils/guc_hooks.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 
@@ -122,8 +123,6 @@
  * ----------
  */
 
-/* minimum interval non-forced stats flushes.*/
-#define PGSTAT_MIN_INTERVAL			1000
 /* how long until to block flushing pending stats updates */
 #define PGSTAT_MAX_INTERVAL			60000
 /* when to call pgstat_report_stat() again, even when idle */
@@ -187,7 +186,8 @@ static void pgstat_init_snapshot_fixed(void);
 
 static void pgstat_reset_after_failure(void);
 
-static bool pgstat_flush_pending_entries(bool nowait);
+static bool pgstat_flush_pending_entries(bool nowait, bool anytime_only);
+static bool pgstat_flush_fixed_stats(bool nowait, bool anytime_only);
 
 static void pgstat_prep_snapshot(void);
 static void pgstat_build_snapshot(void);
@@ -218,6 +218,12 @@ PgStat_LocalState pgStatLocal;
  */
 bool		pgstat_report_fixed = false;
 
+/*
+ * Track when there is pending anytime flush to avoid relying on
+ * get_timeout_active() in hot pathes.
+ */
+bool		pgstat_pending_anytime = false;
+
 /* ----------
  * Local data
  *
@@ -288,6 +294,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_database entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -305,6 +312,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Relation),
 		.shared_data_off = offsetof(PgStatShared_Relation, stats),
@@ -321,6 +329,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Function),
 		.shared_data_off = offsetof(PgStatShared_Function, stats),
@@ -336,6 +345,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.accessed_across_databases = true,
 
@@ -353,6 +363,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_subscription_stats entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -370,6 +381,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = false,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.accessed_across_databases = true,
 
@@ -436,6 +448,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
@@ -453,6 +466,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, slru),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, slru),
@@ -470,6 +484,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, wal),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, wal),
@@ -775,23 +790,11 @@ pgstat_report_stat(bool force)
 	partial_flush = false;
 
 	/* flush of variable-numbered stats tracked in pending entries list */
-	partial_flush |= pgstat_flush_pending_entries(nowait);
+	partial_flush |= pgstat_flush_pending_entries(nowait, false);
 
 	/* flush of other stats kinds */
 	if (pgstat_report_fixed)
-	{
-		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;
-
-			partial_flush |= kind_info->flush_static_cb(nowait);
-		}
-	}
+		partial_flush |= pgstat_flush_fixed_stats(nowait, false);
 
 	last_flush = now;
 
@@ -1293,7 +1296,8 @@ pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid, uint64 objid, bool *creat
 
 	if (entry_ref->pending == NULL)
 	{
-		size_t		entrysize = pgstat_get_kind_info(kind)->pending_size;
+		const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
+		size_t		entrysize = kind_info->pending_size;
 
 		Assert(entrysize != (size_t) -1);
 
@@ -1345,9 +1349,14 @@ pgstat_delete_pending_entry(PgStat_EntryRef *entry_ref)
 
 /*
  * Flush out pending variable-numbered stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME entries.
+ * This is safe to call inside transactions.
+ *
+ * If anytime_only is false, flushes all entries.
  */
 static bool
-pgstat_flush_pending_entries(bool nowait)
+pgstat_flush_pending_entries(bool nowait, bool anytime_only)
 {
 	bool		have_pending = false;
 	dlist_node *cur = NULL;
@@ -1377,8 +1386,22 @@ pgstat_flush_pending_entries(bool nowait)
 		Assert(!kind_info->fixed_amount);
 		Assert(kind_info->flush_pending_cb != NULL);
 
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+		{
+			have_pending = true;
+
+			if (dlist_has_next(&pgStatPending, cur))
+				next = dlist_next_node(&pgStatPending, cur);
+			else
+				next = NULL;
+
+			cur = next;
+			continue;
+		}
+
 		/* flush the stats, if possible */
-		did_flush = kind_info->flush_pending_cb(entry_ref, nowait);
+		did_flush = kind_info->flush_pending_cb(entry_ref, nowait, anytime_only);
 
 		Assert(did_flush || nowait);
 
@@ -1402,6 +1425,33 @@ pgstat_flush_pending_entries(bool nowait)
 	return have_pending;
 }
 
+/*
+ * Flush fixed-amount stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME stats (safe inside transactions).
+ * If anytime_only is false, flushes all stats with flush_static_cb.
+ */
+static bool
+pgstat_flush_fixed_stats(bool nowait, bool anytime_only)
+{
+	bool		partial_flush = false;
+
+	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 || !kind_info->flush_static_cb)
+			continue;
+
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+			continue;
+
+		partial_flush |= kind_info->flush_static_cb(nowait, anytime_only);
+	}
+
+	return partial_flush;
+}
 
 /* ------------------------------------------------------------
  * Helper / infrastructure functions
@@ -2119,3 +2169,33 @@ assign_stats_fetch_consistency(int newval, void *extra)
 	if (pgstat_fetch_consistency != newval)
 		force_stats_snapshot_clear = true;
 }
+
+/*
+ * Flushes only FLUSH_ANYTIME stats using non-blocking locks. Transactional
+ * stats (FLUSH_AT_TXN_BOUNDARY) remain pending until transaction boundary.
+ * Safe to call inside transactions.
+ */
+void
+pgstat_report_anytime_stat(bool force)
+{
+	bool		nowait = !force;
+
+	pgstat_assert_is_up();
+
+	/* Flush stats outside of transaction boundary */
+	pgstat_flush_pending_entries(nowait, true);
+	pgstat_flush_fixed_stats(nowait, true);
+
+	pgstat_pending_anytime = false;
+}
+
+/*
+ * Timeout handler for flushing anytime stats.
+ */
+void
+AnytimeStatsUpdateTimeoutHandler(void)
+{
+	AnytimeStatsUpdateTimeoutPending = true;
+	InterruptPending = true;
+	SetLatch(MyLatch);
+}
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index f2f8d3ff75f..b09316d3ab3 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -31,6 +31,7 @@
 #include "storage/procarray.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 
 /*
  * Backend statistics counts waiting to be flushed out. These counters may be
@@ -66,6 +67,9 @@ pgstat_count_backend_io_op_time(IOObject io_object, IOContext io_context,
 	INSTR_TIME_ADD(PendingBackendStats.pending_io.pending_times[io_object][io_context][io_op],
 				   io_time);
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	backend_has_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -82,6 +86,9 @@ pgstat_count_backend_io_op(IOObject io_object, IOContext io_context,
 	PendingBackendStats.pending_io.counts[io_object][io_context][io_op] += cnt;
 	PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	backend_has_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -268,7 +275,7 @@ pgstat_flush_backend_entry_wal(PgStat_EntryRef *entry_ref)
  * if some statistics could not be flushed due to lock contention.
  */
 bool
-pgstat_flush_backend(bool nowait, bits32 flags)
+pgstat_flush_backend(bool nowait, bits32 flags, bool anytime_only)
 {
 	PgStat_EntryRef *entry_ref;
 	bool		has_pending_data = false;
@@ -311,9 +318,9 @@ pgstat_flush_backend(bool nowait, bits32 flags)
  * If some stats could not be flushed due to lock contention, return true.
  */
 bool
-pgstat_backend_flush_cb(bool nowait)
+pgstat_backend_flush_cb(bool nowait, bool anytime_only)
 {
-	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL);
+	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL, anytime_only);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_bgwriter.c b/src/backend/utils/activity/pgstat_bgwriter.c
index ed2fd801189..1c5f0c3ec40 100644
--- a/src/backend/utils/activity/pgstat_bgwriter.c
+++ b/src/backend/utils/activity/pgstat_bgwriter.c
@@ -61,7 +61,7 @@ pgstat_report_bgwriter(void)
 	/*
 	 * Report IO statistics
 	 */
-	pgstat_flush_io(false);
+	pgstat_flush_io(false, true);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_checkpointer.c b/src/backend/utils/activity/pgstat_checkpointer.c
index 1f70194b7a7..2d89a082464 100644
--- a/src/backend/utils/activity/pgstat_checkpointer.c
+++ b/src/backend/utils/activity/pgstat_checkpointer.c
@@ -68,7 +68,7 @@ pgstat_report_checkpointer(void)
 	/*
 	 * Report IO statistics
 	 */
-	pgstat_flush_io(false);
+	pgstat_flush_io(false, true);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_database.c b/src/backend/utils/activity/pgstat_database.c
index 933dcb5cae5..8e86df60461 100644
--- a/src/backend/utils/activity/pgstat_database.c
+++ b/src/backend/utils/activity/pgstat_database.c
@@ -435,7 +435,7 @@ pgstat_reset_database_timestamp(Oid dboid, TimestampTz ts)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStatShared_Database *sharedent;
 	PgStat_StatDBEntry *pendingent;
diff --git a/src/backend/utils/activity/pgstat_function.c b/src/backend/utils/activity/pgstat_function.c
index e6b84283c6c..5ba4958382f 100644
--- a/src/backend/utils/activity/pgstat_function.c
+++ b/src/backend/utils/activity/pgstat_function.c
@@ -190,11 +190,13 @@ pgstat_end_function_usage(PgStat_FunctionCallUsage *fcu, bool finalize)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_FunctionCounts *localent;
 	PgStatShared_Function *shfuncent;
 
+	Assert(!anytime_only);
+
 	localent = (PgStat_FunctionCounts *) entry_ref->pending;
 	shfuncent = (PgStatShared_Function *) entry_ref->shared_stats;
 
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 28de24538dc..7cd32900236 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -19,6 +19,7 @@
 #include "executor/instrument.h"
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
@@ -79,6 +80,9 @@ pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op,
 	/* Add the per-backend counts */
 	pgstat_count_backend_io_op(io_object, io_context, io_op, cnt, bytes);
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	have_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -172,9 +176,9 @@ pgstat_fetch_stat_io(void)
  * Simpler wrapper of pgstat_io_flush_cb()
  */
 void
-pgstat_flush_io(bool nowait)
+pgstat_flush_io(bool nowait, bool anytime_only)
 {
-	(void) pgstat_io_flush_cb(nowait);
+	(void) pgstat_io_flush_cb(nowait, anytime_only);
 }
 
 /*
@@ -186,7 +190,7 @@ pgstat_flush_io(bool nowait)
  * acquired. Otherwise, return false.
  */
 bool
-pgstat_io_flush_cb(bool nowait)
+pgstat_io_flush_cb(bool nowait, bool anytime_only)
 {
 	LWLock	   *bktype_lock;
 	PgStat_BktypeIO *bktype_shstats;
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..04d21483d93 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -267,8 +267,8 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	 * is done -- which will likely vacuum many relations -- or until the
 	 * VACUUM command has processed all tables and committed.
 	 */
-	pgstat_flush_io(false);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(false, true);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -362,8 +362,8 @@ pgstat_report_analyze(Relation rel,
 	pgstat_unlock_entry(entry_ref);
 
 	/* see pgstat_report_vacuum() */
-	pgstat_flush_io(false);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(false, true);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -812,7 +812,7 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
  * entry when successfully flushing.
  */
 bool
-pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	Oid			dboid;
 	PgStat_TableStatus *lstats; /* pending stats entry  */
@@ -820,6 +820,8 @@ pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
 	PgStat_StatTabEntry *tabentry;	/* table entry of shared stats */
 	PgStat_StatDBEntry *dbentry;	/* pending database entry */
 
+	Assert(!anytime_only);
+
 	dboid = entry_ref->shared_entry->key.dboid;
 	lstats = (PgStat_TableStatus *) entry_ref->pending;
 	shtabstats = (PgStatShared_Relation *) entry_ref->shared_stats;
diff --git a/src/backend/utils/activity/pgstat_slru.c b/src/backend/utils/activity/pgstat_slru.c
index 2190f388eae..bf8a4d58673 100644
--- a/src/backend/utils/activity/pgstat_slru.c
+++ b/src/backend/utils/activity/pgstat_slru.c
@@ -19,6 +19,7 @@
 
 #include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
+#include "utils/timeout.h"
 
 
 static inline PgStat_SLRUStats *get_slru_entry(int slru_idx);
@@ -139,7 +140,7 @@ pgstat_get_slru_index(const char *name)
  * acquired. Otherwise return false.
  */
 bool
-pgstat_slru_flush_cb(bool nowait)
+pgstat_slru_flush_cb(bool nowait, bool anytime_only)
 {
 	PgStatShared_SLRU *stats_shmem = &pgStatLocal.shmem->slru;
 	int			i;
@@ -223,6 +224,9 @@ get_slru_entry(int slru_idx)
 
 	Assert((slru_idx >= 0) && (slru_idx < SLRU_NUM_ELEMENTS));
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	have_slrustats = true;
 	pgstat_report_fixed = true;
 
diff --git a/src/backend/utils/activity/pgstat_subscription.c b/src/backend/utils/activity/pgstat_subscription.c
index 500b1899188..c4614817966 100644
--- a/src/backend/utils/activity/pgstat_subscription.c
+++ b/src/backend/utils/activity/pgstat_subscription.c
@@ -116,11 +116,13 @@ pgstat_fetch_stat_subscription(Oid subid)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_BackendSubEntry *localent;
 	PgStatShared_Subscription *shsubent;
 
+	Assert(!anytime_only);
+
 	localent = (PgStat_BackendSubEntry *) entry_ref->pending;
 	shsubent = (PgStatShared_Subscription *) entry_ref->shared_stats;
 
diff --git a/src/backend/utils/activity/pgstat_wal.c b/src/backend/utils/activity/pgstat_wal.c
index 183e0a7a97b..2c2f3f10e10 100644
--- a/src/backend/utils/activity/pgstat_wal.c
+++ b/src/backend/utils/activity/pgstat_wal.c
@@ -51,12 +51,12 @@ pgstat_report_wal(bool force)
 	nowait = !force;
 
 	/* flush wal stats */
-	(void) pgstat_wal_flush_cb(nowait);
-	pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_WAL);
+	(void) pgstat_wal_flush_cb(nowait, true);
+	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_WAL, true);
 
 	/* flush IO stats */
-	pgstat_flush_io(nowait);
-	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(nowait, true);
+	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -88,7 +88,7 @@ pgstat_wal_have_pending(void)
  * acquired. Otherwise return false.
  */
 bool
-pgstat_wal_flush_cb(bool nowait)
+pgstat_wal_flush_cb(bool nowait, bool anytime_only)
 {
 	PgStatShared_Wal *stats_shmem = &pgStatLocal.shmem->wal;
 	WalUsage	wal_usage_diff = {0};
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 36ad708b360..ad44826c39e 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -40,6 +40,7 @@ volatile sig_atomic_t IdleSessionTimeoutPending = false;
 volatile sig_atomic_t ProcSignalBarrierPending = false;
 volatile sig_atomic_t LogMemoryContextPending = false;
 volatile sig_atomic_t IdleStatsUpdateTimeoutPending = false;
+volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending = false;
 volatile uint32 InterruptHoldoffCount = 0;
 volatile uint32 QueryCancelHoldoffCount = 0;
 volatile uint32 CritSectionCount = 0;
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index b59e08605cc..eeeac1bf39a 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -64,6 +64,7 @@
 #include "utils/injection_point.h"
 #include "utils/memutils.h"
 #include "utils/pg_locale.h"
+#include "utils/pgstat_internal.h"
 #include "utils/portal.h"
 #include "utils/ps_status.h"
 #include "utils/snapmgr.h"
@@ -773,6 +774,8 @@ InitPostgres(const char *in_dbname, Oid dboid,
 		RegisterTimeout(CLIENT_CONNECTION_CHECK_TIMEOUT, ClientCheckTimeoutHandler);
 		RegisterTimeout(IDLE_STATS_UPDATE_TIMEOUT,
 						IdleStatsUpdateTimeoutHandler);
+		RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT,
+						AnytimeStatsUpdateTimeoutHandler);
 	}
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index f16f35659b9..84e698da214 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -96,6 +96,7 @@ extern PGDLLIMPORT volatile sig_atomic_t IdleSessionTimeoutPending;
 extern PGDLLIMPORT volatile sig_atomic_t ProcSignalBarrierPending;
 extern PGDLLIMPORT volatile sig_atomic_t LogMemoryContextPending;
 extern PGDLLIMPORT volatile sig_atomic_t IdleStatsUpdateTimeoutPending;
+extern PGDLLIMPORT volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending;
 
 extern PGDLLIMPORT volatile sig_atomic_t CheckClientConnectionPending;
 extern PGDLLIMPORT volatile sig_atomic_t ClientConnectionLost;
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index fff7ecc2533..f0f546d419a 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -35,6 +35,9 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/* Minimum interval non-forced stats flushes */
+#define PGSTAT_MIN_INTERVAL	1000
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -533,8 +536,24 @@ extern void pgstat_initialize(void);
 
 /* Functions called from backends */
 extern long pgstat_report_stat(bool force);
+extern void pgstat_report_anytime_stat(bool force);
 extern void pgstat_force_next_flush(void);
 
+/*
+ * Schedule the next anytime stats update timeout.
+ *
+ * This should be called whenever accumulating statistics that support
+ * FLUSH_ANYTIME flushing mode.
+ */
+#define pgstat_schedule_anytime_update()												\
+	do {																				\
+		if (IsUnderPostmaster && !pgstat_pending_anytime)								\
+		{																				\
+			enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);	\
+			pgstat_pending_anytime = true;												\
+		}																				\
+	} while (0)
+
 extern void pgstat_reset_counters(void);
 extern void pgstat_reset(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_reset_of_kind(PgStat_Kind kind);
@@ -808,6 +827,8 @@ extern PgStat_WalStats *pgstat_fetch_stat_wal(void);
  * Variables in pgstat.c
  */
 
+extern PGDLLIMPORT bool pgstat_pending_anytime;
+
 /* GUC parameters */
 extern PGDLLIMPORT bool pgstat_track_counts;
 extern PGDLLIMPORT int pgstat_track_functions;
@@ -851,4 +872,5 @@ extern PGDLLIMPORT PgStat_Counter pgStatTransactionIdleTime;
 /* updated by the traffic cop and in errfinish() */
 extern PGDLLIMPORT SessionEndType pgStatSessionEndCause;
 
+
 #endif							/* PGSTAT_H */
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..607f4255268 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -224,6 +224,19 @@ typedef struct PgStat_SubXactStatus
 	PgStat_TableXactStatus *first;	/* head of list for this subxact */
 } PgStat_SubXactStatus;
 
+/*
+ * Flush mode for statistics kinds.
+ *
+ * FLUSH_AT_TXN_BOUNDARY has to be the first because we want it to be the
+ * default value.
+ */
+typedef enum PgStat_FlushMode
+{
+	FLUSH_AT_TXN_BOUNDARY,		/* All fields can only be flushed at
+								 * transaction boundary */
+	FLUSH_ANYTIME,				/* All fields can be flushed anytime,
+								 * including within transactions */
+} PgStat_FlushMode;
 
 /*
  * Metadata for a specific kind of statistics.
@@ -251,6 +264,16 @@ typedef struct PgStat_KindInfo
 	 */
 	bool		track_entry_count:1;
 
+	/*
+	 * The mode of when to flush stats. See PgStat_FlushMode for more details.
+	 *
+	 * This member only has meaning for statistics kinds that accumulate
+	 * pending stats and use flush callbacks. For kinds that write directly to
+	 * shared memory (e.g., archiver, bgwriter, checkpointer), this member has
+	 * no effect.
+	 */
+	PgStat_FlushMode flush_mode;
+
 	/*
 	 * The size of an entry in the shared stats hash table (pointed to by
 	 * PgStatShared_HashEntry->body).  For fixed-numbered statistics, this is
@@ -297,8 +320,10 @@ typedef struct PgStat_KindInfo
 	 * For variable-numbered stats: flush pending stats. Required if pending
 	 * data is used. See flush_static_cb when dealing with stats data that
 	 * that cannot use PgStat_EntryRef->pending.
+	 *
+	 * The anytime_only parameter indicates whether this is an anytime flush.
 	 */
-	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait);
+	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait, bool anytime_only);
 
 	/*
 	 * For variable-numbered stats: delete pending stats. Optional.
@@ -366,8 +391,10 @@ typedef struct PgStat_KindInfo
 	 *
 	 * "pgstat_report_fixed" needs to be set to trigger the flush of pending
 	 * stats.
+	 *
+	 * The anytime_only parameter indicates whether this is an anytime flush.
 	 */
-	bool		(*flush_static_cb) (bool nowait);
+	bool		(*flush_static_cb) (bool nowait, bool anytime_only);
 
 	/*
 	 * For fixed-numbered statistics: Reset All.
@@ -677,6 +704,7 @@ extern PgStat_EntryRef *pgstat_fetch_pending_entry(PgStat_Kind kind,
 
 extern void *pgstat_fetch_entry(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_snapshot_fixed(PgStat_Kind kind);
+extern void AnytimeStatsUpdateTimeoutHandler(void);
 
 
 /*
@@ -696,8 +724,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL)
 
-extern bool pgstat_flush_backend(bool nowait, bits32 flags);
-extern bool pgstat_backend_flush_cb(bool nowait);
+extern bool pgstat_flush_backend(bool nowait, bits32 flags, bool anytime_only);
+extern bool pgstat_backend_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header,
 											  TimestampTz ts);
 
@@ -729,7 +757,7 @@ extern void AtEOXact_PgStat_Database(bool isCommit, bool parallel);
 
 extern PgStat_StatDBEntry *pgstat_prep_database_pending(Oid dboid);
 extern void pgstat_reset_database_timestamp(Oid dboid, TimestampTz ts);
-extern bool pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_database_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
@@ -737,7 +765,7 @@ extern void pgstat_database_reset_timestamp_cb(PgStatShared_Common *header, Time
  * Functions in pgstat_function.c
  */
 
-extern bool pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_function_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
@@ -745,9 +773,9 @@ extern void pgstat_function_reset_timestamp_cb(PgStatShared_Common *header, Time
  * Functions in pgstat_io.c
  */
 
-extern void pgstat_flush_io(bool nowait);
+extern void pgstat_flush_io(bool nowait, bool anytime_only);
 
-extern bool pgstat_io_flush_cb(bool nowait);
+extern bool pgstat_io_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_io_init_shmem_cb(void *stats);
 extern void pgstat_io_reset_all_cb(TimestampTz ts);
 extern void pgstat_io_snapshot_cb(void);
@@ -762,7 +790,7 @@ extern void AtEOSubXact_PgStat_Relations(PgStat_SubXactStatus *xact_state, bool
 extern void AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 
-extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
@@ -809,7 +837,7 @@ extern PgStatShared_Common *pgstat_init_entry(PgStat_Kind kind,
  * Functions in pgstat_slru.c
  */
 
-extern bool pgstat_slru_flush_cb(bool nowait);
+extern bool pgstat_slru_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_slru_init_shmem_cb(void *stats);
 extern void pgstat_slru_reset_all_cb(TimestampTz ts);
 extern void pgstat_slru_snapshot_cb(void);
@@ -820,7 +848,7 @@ extern void pgstat_slru_snapshot_cb(void);
  */
 
 extern void pgstat_wal_init_backend_cb(void);
-extern bool pgstat_wal_flush_cb(bool nowait);
+extern bool pgstat_wal_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_wal_init_shmem_cb(void *stats);
 extern void pgstat_wal_reset_all_cb(TimestampTz ts);
 extern void pgstat_wal_snapshot_cb(void);
@@ -830,7 +858,7 @@ extern void pgstat_wal_snapshot_cb(void);
  * Functions in pgstat_subscription.c
  */
 
-extern bool pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_subscription_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h
index 0965b590b34..10723bb664c 100644
--- a/src/include/utils/timeout.h
+++ b/src/include/utils/timeout.h
@@ -35,6 +35,7 @@ typedef enum TimeoutId
 	IDLE_SESSION_TIMEOUT,
 	IDLE_STATS_UPDATE_TIMEOUT,
 	CLIENT_CONNECTION_CHECK_TIMEOUT,
+	ANYTIME_STATS_UPDATE_TIMEOUT,
 	STARTUP_PROGRESS_TIMEOUT,
 	/* First user-definable timeout reason */
 	USER_TIMEOUT,
diff --git a/src/test/modules/test_custom_stats/test_custom_var_stats.c b/src/test/modules/test_custom_stats/test_custom_var_stats.c
index 64a8fe63cce..bc0b5d6e0eb 100644
--- a/src/test/modules/test_custom_stats/test_custom_var_stats.c
+++ b/src/test/modules/test_custom_stats/test_custom_var_stats.c
@@ -83,7 +83,7 @@ static dsa_area *custom_stats_description_dsa = NULL;
 
 /* Flush callback: merge pending stats into shared memory */
 static bool test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref,
-												   bool nowait);
+												   bool nowait, bool anytime_only);
 
 /* Serialization callback: write auxiliary entry data */
 static void test_custom_stats_var_to_serialized_data(const PgStat_HashKey *key,
@@ -150,7 +150,7 @@ _PG_init(void)
  * Returns false only if nowait=true and lock acquisition fails.
  */
 static bool
-test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref, bool nowait)
+test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_StatCustomVarEntry *pending_entry;
 	PgStatShared_CustomVarEntry *shared_entry;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 241945734ec..1dbc4b96f51 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2271,6 +2271,7 @@ PgStat_Counter
 PgStat_EntryRef
 PgStat_EntryRefHashEntry
 PgStat_FetchConsistency
+PgStat_FlushMode
 PgStat_FunctionCallUsage
 PgStat_FunctionCounts
 PgStat_HashKey
-- 
2.34.1


--aq/6bi8L6WORnI+9
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v9-0002-Add-anytime-flush-tests-for-custom-stats.patch"



^ permalink  raw  reply  [nested|flat] 12+ messages in thread

* [PATCH v11 1/5] Add pgstat_report_anytime_stat() for periodic stats flushing
@ 2026-01-05 09:41 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-05 09:41 UTC (permalink / raw)

Long running transactions can accumulate significant statistics (WAL, IO, ...)
that remain unflushed until the transaction ends. This delays visibility of
resource usage in monitoring views like pg_stat_io and pg_stat_wal and produces
spikes when flushed.

This commit introduces pgstat_report_anytime_stat(), which flushes
non transactional statistics even inside active transactions. A new timeout
handler fires every second (if enabled while adding pending stats) to call this
function, ensuring timely stats visibility without waiting for transaction completion.

Implementation details:

- Add PgStat_FlushMode enum to classify stats kinds:
  * FLUSH_ANYTIME: Stats that can always be flushed (WAL, IO, ...)
  * FLUSH_AT_TXN_BOUNDARY: Stats requiring transaction boundaries

- Modify pgstat_flush_pending_entries() and pgstat_flush_fixed_stats()
  to accept a boolean anytime_only parameter:
  * When false: flushes all stats (existing behavior)
  * When true: flushes only FLUSH_ANYTIME stats and skips FLUSH_AT_TXN_BOUNDARY stats

- The flush_pending_cb and flush_static_cb callbacks now receive an anytime_only
boolean parameter. Most of the time it's not used (except for assertions), but it's
preparatory work for moving the relations stats to anytime (without introducin
a new callback).

- Add pgstat_schedule_anytime_update() macro to schedule the next anytime flush,
relying on PGSTAT_MIN_INTERVAL

The force parameter in pgstat_report_anytime_stat() is currently unused (always
called with force=false) but reserved for future use cases requiring immediate
flushing.
---
 src/backend/access/transam/xlog.c             |   6 +
 src/backend/postmaster/bgwriter.c             |   9 +-
 src/backend/postmaster/checkpointer.c         |  10 +-
 src/backend/postmaster/startup.c              |   2 +
 src/backend/postmaster/walsummarizer.c        |   9 +-
 src/backend/postmaster/walwriter.c            |   9 +-
 src/backend/replication/walreceiver.c         |   9 +-
 src/backend/replication/walsender.c           |   8 +-
 src/backend/tcop/postgres.c                   |  12 ++
 src/backend/utils/activity/pgstat.c           | 121 +++++++++++++++---
 src/backend/utils/activity/pgstat_backend.c   |  13 +-
 src/backend/utils/activity/pgstat_bgwriter.c  |   2 +-
 .../utils/activity/pgstat_checkpointer.c      |   2 +-
 src/backend/utils/activity/pgstat_database.c  |   2 +-
 src/backend/utils/activity/pgstat_function.c  |   4 +-
 src/backend/utils/activity/pgstat_io.c        |  10 +-
 src/backend/utils/activity/pgstat_relation.c  |  12 +-
 src/backend/utils/activity/pgstat_slru.c      |   6 +-
 .../utils/activity/pgstat_subscription.c      |   4 +-
 src/backend/utils/activity/pgstat_wal.c       |  10 +-
 src/backend/utils/init/globals.c              |   1 +
 src/backend/utils/init/postinit.c             |   3 +
 src/include/miscadmin.h                       |   1 +
 src/include/pgstat.h                          |  22 ++++
 src/include/utils/pgstat_internal.h           |  52 ++++++--
 src/include/utils/timeout.h                   |   1 +
 .../test_custom_stats/test_custom_var_stats.c |   4 +-
 src/tools/pgindent/typedefs.list              |   1 +
 28 files changed, 279 insertions(+), 66 deletions(-)
  10.5% src/backend/postmaster/
   5.8% src/backend/replication/
  51.0% src/backend/utils/activity/
   5.8% src/backend/
  18.7% src/include/utils/
   6.6% src/include/

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13cce9b49f1..cf29fc91f70 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -1085,6 +1085,9 @@ XLogInsertRecord(XLogRecData *rdata,
 		pgWalUsage.wal_fpi += num_fpi;
 		pgWalUsage.wal_fpi_bytes += fpi_bytes;
 
+		/* Schedule next anytime stats update timeout */
+		pgstat_schedule_anytime_update();
+
 		/* Required for the flush of pending stats WAL data */
 		pgstat_report_fixed = true;
 	}
@@ -2066,6 +2069,9 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic)
 					pgWalUsage.wal_buffers_full++;
 					TRACE_POSTGRESQL_WAL_BUFFER_WRITE_DIRTY_DONE();
 
+					/* Schedule next anytime stats update timeout */
+					pgstat_schedule_anytime_update();
+
 					/*
 					 * Required for the flush of pending stats WAL data, per
 					 * update of pgWalUsage.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 0956bd39a85..059c601c3b8 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -49,7 +49,9 @@
 #include "storage/smgr.h"
 #include "storage/standby.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 /*
@@ -103,7 +105,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN);
@@ -113,6 +115,11 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * We just started, assume there has been either a shutdown or
 	 * end-of-recovery snapshot.
diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c
index e03c19123bc..e11c4b099c8 100644
--- a/src/backend/postmaster/checkpointer.c
+++ b/src/backend/postmaster/checkpointer.c
@@ -66,8 +66,9 @@
 #include "utils/acl.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
-
+#include "utils/timeout.h"
 
 /*----------
  * Shared memory area for communication between checkpointer and backends
@@ -215,7 +216,7 @@ CheckpointerMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, ReqShutdownXLOG);
 	pqsignal(SIGTERM, SIG_IGN); /* ignore SIGTERM */
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SignalHandlerForShutdownRequest);
@@ -225,6 +226,11 @@ CheckpointerMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * Initialize so that first time-driven event happens at the correct time.
 	 */
diff --git a/src/backend/postmaster/startup.c b/src/backend/postmaster/startup.c
index cdbe53dd262..4954fe425b7 100644
--- a/src/backend/postmaster/startup.c
+++ b/src/backend/postmaster/startup.c
@@ -32,6 +32,7 @@
 #include "storage/standby.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timeout.h"
 
 
@@ -245,6 +246,7 @@ StartupProcessMain(const void *startup_data, size_t startup_data_len)
 	RegisterTimeout(STANDBY_DEADLOCK_TIMEOUT, StandbyDeadLockHandler);
 	RegisterTimeout(STANDBY_TIMEOUT, StandbyTimeoutHandler);
 	RegisterTimeout(STANDBY_LOCK_TIMEOUT, StandbyLockTimeoutHandler);
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
 
 	/*
 	 * Unblock signals (they were blocked when the postmaster forked us)
diff --git a/src/backend/postmaster/walsummarizer.c b/src/backend/postmaster/walsummarizer.c
index 742137edad6..f1bae9d23d6 100644
--- a/src/backend/postmaster/walsummarizer.c
+++ b/src/backend/postmaster/walsummarizer.c
@@ -48,6 +48,8 @@
 #include "storage/shmem.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 #include "utils/wait_event.h"
 
 /*
@@ -246,7 +248,7 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);	/* no query to cancel */
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN); /* not used */
@@ -268,6 +270,11 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * If an exception is encountered, processing resumes here.
 	 */
diff --git a/src/backend/postmaster/walwriter.c b/src/backend/postmaster/walwriter.c
index 7c0e2809c17..bcf59227a00 100644
--- a/src/backend/postmaster/walwriter.c
+++ b/src/backend/postmaster/walwriter.c
@@ -61,7 +61,9 @@
 #include "storage/smgr.h"
 #include "utils/hsearch.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
+#include "utils/timeout.h"
 
 
 /*
@@ -103,7 +105,7 @@ WalWriterMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);	/* no query to cancel */
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN); /* not used */
@@ -113,6 +115,11 @@ WalWriterMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * Create a memory context that we will do all our work in.  We do this so
 	 * that we can reset the context during error recovery and thereby avoid
diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index 7c1b8757d7d..aecc7a127e6 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -77,7 +77,9 @@
 #include "utils/builtins.h"
 #include "utils/guc.h"
 #include "utils/pg_lsn.h"
+#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 
@@ -252,7 +254,7 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);
 	pqsignal(SIGTERM, die);		/* request shutdown */
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN);
@@ -260,6 +262,11 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/* Load the libpq-specific functions */
 	load_file("libpqwalreceiver", false);
 	if (WalReceiverFunctions == NULL)
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 2cde8ebc729..a7214d0dc6f 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -1987,8 +1987,8 @@ WalSndWaitForWal(XLogRecPtr loc)
 		if (TimestampDifferenceExceeds(last_flush, now,
 									   WALSENDER_STATS_FLUSH_INTERVAL))
 		{
-			pgstat_flush_io(false);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+			pgstat_flush_io(false, true);
+			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 			last_flush = now;
 		}
 
@@ -3016,8 +3016,8 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			if (TimestampDifferenceExceeds(last_flush, now,
 										   WALSENDER_STATS_FLUSH_INTERVAL))
 			{
-				pgstat_flush_io(false);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+				pgstat_flush_io(false, true);
+				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 				last_flush = now;
 			}
 
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index d01a09dd0c4..8c30efa2443 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -3564,6 +3564,18 @@ ProcessInterrupts(void)
 		pgstat_report_stat(true);
 	}
 
+	/*
+	 * Flush stats outside of transaction boundary if the timeout fired.
+	 * Unlike transactional stats, these can be flushed even inside a running
+	 * transaction.
+	 */
+	if (AnytimeStatsUpdateTimeoutPending)
+	{
+		AnytimeStatsUpdateTimeoutPending = false;
+
+		pgstat_report_anytime_stat(false);
+	}
+
 	if (ProcSignalBarrierPending)
 		ProcessProcSignalBarrier();
 
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 11bb71cad5a..ddd331e2c81 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -108,10 +108,12 @@
 #include "pgstat.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
+#include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "utils/guc_hooks.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 
@@ -122,8 +124,6 @@
  * ----------
  */
 
-/* minimum interval non-forced stats flushes.*/
-#define PGSTAT_MIN_INTERVAL			1000
 /* how long until to block flushing pending stats updates */
 #define PGSTAT_MAX_INTERVAL			60000
 /* when to call pgstat_report_stat() again, even when idle */
@@ -187,7 +187,8 @@ static void pgstat_init_snapshot_fixed(void);
 
 static void pgstat_reset_after_failure(void);
 
-static bool pgstat_flush_pending_entries(bool nowait);
+static bool pgstat_flush_pending_entries(bool nowait, bool anytime_only);
+static bool pgstat_flush_fixed_stats(bool nowait, bool anytime_only);
 
 static void pgstat_prep_snapshot(void);
 static void pgstat_build_snapshot(void);
@@ -218,6 +219,12 @@ PgStat_LocalState pgStatLocal;
  */
 bool		pgstat_report_fixed = false;
 
+/*
+ * Track when there is pending anytime flush to avoid relying on
+ * get_timeout_active() in hot pathes.
+ */
+bool		pgstat_pending_anytime = false;
+
 /* ----------
  * Local data
  *
@@ -288,6 +295,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_database entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -305,6 +313,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Relation),
 		.shared_data_off = offsetof(PgStatShared_Relation, stats),
@@ -321,6 +330,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Function),
 		.shared_data_off = offsetof(PgStatShared_Function, stats),
@@ -336,6 +346,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.accessed_across_databases = true,
 
@@ -353,6 +364,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_subscription_stats entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -370,6 +382,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = false,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.accessed_across_databases = true,
 
@@ -436,6 +449,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
@@ -453,6 +467,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, slru),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, slru),
@@ -470,6 +485,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, wal),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, wal),
@@ -775,23 +791,11 @@ pgstat_report_stat(bool force)
 	partial_flush = false;
 
 	/* flush of variable-numbered stats tracked in pending entries list */
-	partial_flush |= pgstat_flush_pending_entries(nowait);
+	partial_flush |= pgstat_flush_pending_entries(nowait, false);
 
 	/* flush of other stats kinds */
 	if (pgstat_report_fixed)
-	{
-		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;
-
-			partial_flush |= kind_info->flush_static_cb(nowait);
-		}
-	}
+		partial_flush |= pgstat_flush_fixed_stats(nowait, false);
 
 	last_flush = now;
 
@@ -1293,7 +1297,8 @@ pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid, uint64 objid, bool *creat
 
 	if (entry_ref->pending == NULL)
 	{
-		size_t		entrysize = pgstat_get_kind_info(kind)->pending_size;
+		const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
+		size_t		entrysize = kind_info->pending_size;
 
 		Assert(entrysize != (size_t) -1);
 
@@ -1345,9 +1350,14 @@ pgstat_delete_pending_entry(PgStat_EntryRef *entry_ref)
 
 /*
  * Flush out pending variable-numbered stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME entries.
+ * This is safe to call inside transactions.
+ *
+ * If anytime_only is false, flushes all entries.
  */
 static bool
-pgstat_flush_pending_entries(bool nowait)
+pgstat_flush_pending_entries(bool nowait, bool anytime_only)
 {
 	bool		have_pending = false;
 	dlist_node *cur = NULL;
@@ -1377,8 +1387,22 @@ pgstat_flush_pending_entries(bool nowait)
 		Assert(!kind_info->fixed_amount);
 		Assert(kind_info->flush_pending_cb != NULL);
 
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+		{
+			have_pending = true;
+
+			if (dlist_has_next(&pgStatPending, cur))
+				next = dlist_next_node(&pgStatPending, cur);
+			else
+				next = NULL;
+
+			cur = next;
+			continue;
+		}
+
 		/* flush the stats, if possible */
-		did_flush = kind_info->flush_pending_cb(entry_ref, nowait);
+		did_flush = kind_info->flush_pending_cb(entry_ref, nowait, anytime_only);
 
 		Assert(did_flush || nowait);
 
@@ -1402,6 +1426,33 @@ pgstat_flush_pending_entries(bool nowait)
 	return have_pending;
 }
 
+/*
+ * Flush fixed-amount stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME stats (safe inside transactions).
+ * If anytime_only is false, flushes all stats with flush_static_cb.
+ */
+static bool
+pgstat_flush_fixed_stats(bool nowait, bool anytime_only)
+{
+	bool		partial_flush = false;
+
+	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 || !kind_info->flush_static_cb)
+			continue;
+
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+			continue;
+
+		partial_flush |= kind_info->flush_static_cb(nowait, anytime_only);
+	}
+
+	return partial_flush;
+}
 
 /* ------------------------------------------------------------
  * Helper / infrastructure functions
@@ -2119,3 +2170,33 @@ assign_stats_fetch_consistency(int newval, void *extra)
 	if (pgstat_fetch_consistency != newval)
 		force_stats_snapshot_clear = true;
 }
+
+/*
+ * Flushes only FLUSH_ANYTIME stats using non-blocking locks. Transactional
+ * stats (FLUSH_AT_TXN_BOUNDARY) remain pending until transaction boundary.
+ * Safe to call inside transactions.
+ */
+void
+pgstat_report_anytime_stat(bool force)
+{
+	bool		nowait = !force;
+
+	pgstat_assert_is_up();
+
+	/* Flush stats outside of transaction boundary */
+	pgstat_flush_pending_entries(nowait, true);
+	pgstat_flush_fixed_stats(nowait, true);
+
+	pgstat_pending_anytime = false;
+}
+
+/*
+ * Timeout handler for flushing anytime stats.
+ */
+void
+AnytimeStatsUpdateTimeoutHandler(void)
+{
+	AnytimeStatsUpdateTimeoutPending = true;
+	InterruptPending = true;
+	SetLatch(MyLatch);
+}
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index f2f8d3ff75f..b09316d3ab3 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -31,6 +31,7 @@
 #include "storage/procarray.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 
 /*
  * Backend statistics counts waiting to be flushed out. These counters may be
@@ -66,6 +67,9 @@ pgstat_count_backend_io_op_time(IOObject io_object, IOContext io_context,
 	INSTR_TIME_ADD(PendingBackendStats.pending_io.pending_times[io_object][io_context][io_op],
 				   io_time);
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	backend_has_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -82,6 +86,9 @@ pgstat_count_backend_io_op(IOObject io_object, IOContext io_context,
 	PendingBackendStats.pending_io.counts[io_object][io_context][io_op] += cnt;
 	PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	backend_has_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -268,7 +275,7 @@ pgstat_flush_backend_entry_wal(PgStat_EntryRef *entry_ref)
  * if some statistics could not be flushed due to lock contention.
  */
 bool
-pgstat_flush_backend(bool nowait, bits32 flags)
+pgstat_flush_backend(bool nowait, bits32 flags, bool anytime_only)
 {
 	PgStat_EntryRef *entry_ref;
 	bool		has_pending_data = false;
@@ -311,9 +318,9 @@ pgstat_flush_backend(bool nowait, bits32 flags)
  * If some stats could not be flushed due to lock contention, return true.
  */
 bool
-pgstat_backend_flush_cb(bool nowait)
+pgstat_backend_flush_cb(bool nowait, bool anytime_only)
 {
-	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL);
+	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL, anytime_only);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_bgwriter.c b/src/backend/utils/activity/pgstat_bgwriter.c
index ed2fd801189..1c5f0c3ec40 100644
--- a/src/backend/utils/activity/pgstat_bgwriter.c
+++ b/src/backend/utils/activity/pgstat_bgwriter.c
@@ -61,7 +61,7 @@ pgstat_report_bgwriter(void)
 	/*
 	 * Report IO statistics
 	 */
-	pgstat_flush_io(false);
+	pgstat_flush_io(false, true);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_checkpointer.c b/src/backend/utils/activity/pgstat_checkpointer.c
index 1f70194b7a7..2d89a082464 100644
--- a/src/backend/utils/activity/pgstat_checkpointer.c
+++ b/src/backend/utils/activity/pgstat_checkpointer.c
@@ -68,7 +68,7 @@ pgstat_report_checkpointer(void)
 	/*
 	 * Report IO statistics
 	 */
-	pgstat_flush_io(false);
+	pgstat_flush_io(false, true);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_database.c b/src/backend/utils/activity/pgstat_database.c
index 933dcb5cae5..8e86df60461 100644
--- a/src/backend/utils/activity/pgstat_database.c
+++ b/src/backend/utils/activity/pgstat_database.c
@@ -435,7 +435,7 @@ pgstat_reset_database_timestamp(Oid dboid, TimestampTz ts)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStatShared_Database *sharedent;
 	PgStat_StatDBEntry *pendingent;
diff --git a/src/backend/utils/activity/pgstat_function.c b/src/backend/utils/activity/pgstat_function.c
index e6b84283c6c..5ba4958382f 100644
--- a/src/backend/utils/activity/pgstat_function.c
+++ b/src/backend/utils/activity/pgstat_function.c
@@ -190,11 +190,13 @@ pgstat_end_function_usage(PgStat_FunctionCallUsage *fcu, bool finalize)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_FunctionCounts *localent;
 	PgStatShared_Function *shfuncent;
 
+	Assert(!anytime_only);
+
 	localent = (PgStat_FunctionCounts *) entry_ref->pending;
 	shfuncent = (PgStatShared_Function *) entry_ref->shared_stats;
 
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 28de24538dc..7cd32900236 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -19,6 +19,7 @@
 #include "executor/instrument.h"
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
@@ -79,6 +80,9 @@ pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op,
 	/* Add the per-backend counts */
 	pgstat_count_backend_io_op(io_object, io_context, io_op, cnt, bytes);
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	have_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -172,9 +176,9 @@ pgstat_fetch_stat_io(void)
  * Simpler wrapper of pgstat_io_flush_cb()
  */
 void
-pgstat_flush_io(bool nowait)
+pgstat_flush_io(bool nowait, bool anytime_only)
 {
-	(void) pgstat_io_flush_cb(nowait);
+	(void) pgstat_io_flush_cb(nowait, anytime_only);
 }
 
 /*
@@ -186,7 +190,7 @@ pgstat_flush_io(bool nowait)
  * acquired. Otherwise, return false.
  */
 bool
-pgstat_io_flush_cb(bool nowait)
+pgstat_io_flush_cb(bool nowait, bool anytime_only)
 {
 	LWLock	   *bktype_lock;
 	PgStat_BktypeIO *bktype_shstats;
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..04d21483d93 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -267,8 +267,8 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	 * is done -- which will likely vacuum many relations -- or until the
 	 * VACUUM command has processed all tables and committed.
 	 */
-	pgstat_flush_io(false);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(false, true);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -362,8 +362,8 @@ pgstat_report_analyze(Relation rel,
 	pgstat_unlock_entry(entry_ref);
 
 	/* see pgstat_report_vacuum() */
-	pgstat_flush_io(false);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(false, true);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -812,7 +812,7 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
  * entry when successfully flushing.
  */
 bool
-pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	Oid			dboid;
 	PgStat_TableStatus *lstats; /* pending stats entry  */
@@ -820,6 +820,8 @@ pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
 	PgStat_StatTabEntry *tabentry;	/* table entry of shared stats */
 	PgStat_StatDBEntry *dbentry;	/* pending database entry */
 
+	Assert(!anytime_only);
+
 	dboid = entry_ref->shared_entry->key.dboid;
 	lstats = (PgStat_TableStatus *) entry_ref->pending;
 	shtabstats = (PgStatShared_Relation *) entry_ref->shared_stats;
diff --git a/src/backend/utils/activity/pgstat_slru.c b/src/backend/utils/activity/pgstat_slru.c
index 2190f388eae..bf8a4d58673 100644
--- a/src/backend/utils/activity/pgstat_slru.c
+++ b/src/backend/utils/activity/pgstat_slru.c
@@ -19,6 +19,7 @@
 
 #include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
+#include "utils/timeout.h"
 
 
 static inline PgStat_SLRUStats *get_slru_entry(int slru_idx);
@@ -139,7 +140,7 @@ pgstat_get_slru_index(const char *name)
  * acquired. Otherwise return false.
  */
 bool
-pgstat_slru_flush_cb(bool nowait)
+pgstat_slru_flush_cb(bool nowait, bool anytime_only)
 {
 	PgStatShared_SLRU *stats_shmem = &pgStatLocal.shmem->slru;
 	int			i;
@@ -223,6 +224,9 @@ get_slru_entry(int slru_idx)
 
 	Assert((slru_idx >= 0) && (slru_idx < SLRU_NUM_ELEMENTS));
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	have_slrustats = true;
 	pgstat_report_fixed = true;
 
diff --git a/src/backend/utils/activity/pgstat_subscription.c b/src/backend/utils/activity/pgstat_subscription.c
index 3277cf88a4e..6b6eec7578d 100644
--- a/src/backend/utils/activity/pgstat_subscription.c
+++ b/src/backend/utils/activity/pgstat_subscription.c
@@ -117,11 +117,13 @@ pgstat_fetch_stat_subscription(Oid subid)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_BackendSubEntry *localent;
 	PgStatShared_Subscription *shsubent;
 
+	Assert(!anytime_only);
+
 	localent = (PgStat_BackendSubEntry *) entry_ref->pending;
 	shsubent = (PgStatShared_Subscription *) entry_ref->shared_stats;
 
diff --git a/src/backend/utils/activity/pgstat_wal.c b/src/backend/utils/activity/pgstat_wal.c
index 183e0a7a97b..2c2f3f10e10 100644
--- a/src/backend/utils/activity/pgstat_wal.c
+++ b/src/backend/utils/activity/pgstat_wal.c
@@ -51,12 +51,12 @@ pgstat_report_wal(bool force)
 	nowait = !force;
 
 	/* flush wal stats */
-	(void) pgstat_wal_flush_cb(nowait);
-	pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_WAL);
+	(void) pgstat_wal_flush_cb(nowait, true);
+	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_WAL, true);
 
 	/* flush IO stats */
-	pgstat_flush_io(nowait);
-	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(nowait, true);
+	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -88,7 +88,7 @@ pgstat_wal_have_pending(void)
  * acquired. Otherwise return false.
  */
 bool
-pgstat_wal_flush_cb(bool nowait)
+pgstat_wal_flush_cb(bool nowait, bool anytime_only)
 {
 	PgStatShared_Wal *stats_shmem = &pgStatLocal.shmem->wal;
 	WalUsage	wal_usage_diff = {0};
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 36ad708b360..ad44826c39e 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -40,6 +40,7 @@ volatile sig_atomic_t IdleSessionTimeoutPending = false;
 volatile sig_atomic_t ProcSignalBarrierPending = false;
 volatile sig_atomic_t LogMemoryContextPending = false;
 volatile sig_atomic_t IdleStatsUpdateTimeoutPending = false;
+volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending = false;
 volatile uint32 InterruptHoldoffCount = 0;
 volatile uint32 QueryCancelHoldoffCount = 0;
 volatile uint32 CritSectionCount = 0;
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index b59e08605cc..eeeac1bf39a 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -64,6 +64,7 @@
 #include "utils/injection_point.h"
 #include "utils/memutils.h"
 #include "utils/pg_locale.h"
+#include "utils/pgstat_internal.h"
 #include "utils/portal.h"
 #include "utils/ps_status.h"
 #include "utils/snapmgr.h"
@@ -773,6 +774,8 @@ InitPostgres(const char *in_dbname, Oid dboid,
 		RegisterTimeout(CLIENT_CONNECTION_CHECK_TIMEOUT, ClientCheckTimeoutHandler);
 		RegisterTimeout(IDLE_STATS_UPDATE_TIMEOUT,
 						IdleStatsUpdateTimeoutHandler);
+		RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT,
+						AnytimeStatsUpdateTimeoutHandler);
 	}
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index f16f35659b9..84e698da214 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -96,6 +96,7 @@ extern PGDLLIMPORT volatile sig_atomic_t IdleSessionTimeoutPending;
 extern PGDLLIMPORT volatile sig_atomic_t ProcSignalBarrierPending;
 extern PGDLLIMPORT volatile sig_atomic_t LogMemoryContextPending;
 extern PGDLLIMPORT volatile sig_atomic_t IdleStatsUpdateTimeoutPending;
+extern PGDLLIMPORT volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending;
 
 extern PGDLLIMPORT volatile sig_atomic_t CheckClientConnectionPending;
 extern PGDLLIMPORT volatile sig_atomic_t ClientConnectionLost;
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 9bb777c3d5a..b011a315679 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -34,6 +34,9 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/* Minimum interval non-forced stats flushes */
+#define PGSTAT_MIN_INTERVAL	1000
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -532,8 +535,24 @@ extern void pgstat_initialize(void);
 
 /* Functions called from backends */
 extern long pgstat_report_stat(bool force);
+extern void pgstat_report_anytime_stat(bool force);
 extern void pgstat_force_next_flush(void);
 
+/*
+ * Schedule the next anytime stats update timeout.
+ *
+ * This should be called whenever accumulating statistics that support
+ * FLUSH_ANYTIME flushing mode.
+ */
+#define pgstat_schedule_anytime_update()												\
+	do {																				\
+		if (IsUnderPostmaster && !pgstat_pending_anytime)								\
+		{																				\
+			enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);	\
+			pgstat_pending_anytime = true;												\
+		}																				\
+	} while (0)
+
 extern void pgstat_reset_counters(void);
 extern void pgstat_reset(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_reset_of_kind(PgStat_Kind kind);
@@ -806,6 +825,8 @@ extern PgStat_WalStats *pgstat_fetch_stat_wal(void);
  * Variables in pgstat.c
  */
 
+extern PGDLLIMPORT bool pgstat_pending_anytime;
+
 /* GUC parameters */
 extern PGDLLIMPORT bool pgstat_track_counts;
 extern PGDLLIMPORT int pgstat_track_functions;
@@ -849,4 +870,5 @@ extern PGDLLIMPORT PgStat_Counter pgStatTransactionIdleTime;
 /* updated by the traffic cop and in errfinish() */
 extern PGDLLIMPORT SessionEndType pgStatSessionEndCause;
 
+
 #endif							/* PGSTAT_H */
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..607f4255268 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -224,6 +224,19 @@ typedef struct PgStat_SubXactStatus
 	PgStat_TableXactStatus *first;	/* head of list for this subxact */
 } PgStat_SubXactStatus;
 
+/*
+ * Flush mode for statistics kinds.
+ *
+ * FLUSH_AT_TXN_BOUNDARY has to be the first because we want it to be the
+ * default value.
+ */
+typedef enum PgStat_FlushMode
+{
+	FLUSH_AT_TXN_BOUNDARY,		/* All fields can only be flushed at
+								 * transaction boundary */
+	FLUSH_ANYTIME,				/* All fields can be flushed anytime,
+								 * including within transactions */
+} PgStat_FlushMode;
 
 /*
  * Metadata for a specific kind of statistics.
@@ -251,6 +264,16 @@ typedef struct PgStat_KindInfo
 	 */
 	bool		track_entry_count:1;
 
+	/*
+	 * The mode of when to flush stats. See PgStat_FlushMode for more details.
+	 *
+	 * This member only has meaning for statistics kinds that accumulate
+	 * pending stats and use flush callbacks. For kinds that write directly to
+	 * shared memory (e.g., archiver, bgwriter, checkpointer), this member has
+	 * no effect.
+	 */
+	PgStat_FlushMode flush_mode;
+
 	/*
 	 * The size of an entry in the shared stats hash table (pointed to by
 	 * PgStatShared_HashEntry->body).  For fixed-numbered statistics, this is
@@ -297,8 +320,10 @@ typedef struct PgStat_KindInfo
 	 * For variable-numbered stats: flush pending stats. Required if pending
 	 * data is used. See flush_static_cb when dealing with stats data that
 	 * that cannot use PgStat_EntryRef->pending.
+	 *
+	 * The anytime_only parameter indicates whether this is an anytime flush.
 	 */
-	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait);
+	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait, bool anytime_only);
 
 	/*
 	 * For variable-numbered stats: delete pending stats. Optional.
@@ -366,8 +391,10 @@ typedef struct PgStat_KindInfo
 	 *
 	 * "pgstat_report_fixed" needs to be set to trigger the flush of pending
 	 * stats.
+	 *
+	 * The anytime_only parameter indicates whether this is an anytime flush.
 	 */
-	bool		(*flush_static_cb) (bool nowait);
+	bool		(*flush_static_cb) (bool nowait, bool anytime_only);
 
 	/*
 	 * For fixed-numbered statistics: Reset All.
@@ -677,6 +704,7 @@ extern PgStat_EntryRef *pgstat_fetch_pending_entry(PgStat_Kind kind,
 
 extern void *pgstat_fetch_entry(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_snapshot_fixed(PgStat_Kind kind);
+extern void AnytimeStatsUpdateTimeoutHandler(void);
 
 
 /*
@@ -696,8 +724,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL)
 
-extern bool pgstat_flush_backend(bool nowait, bits32 flags);
-extern bool pgstat_backend_flush_cb(bool nowait);
+extern bool pgstat_flush_backend(bool nowait, bits32 flags, bool anytime_only);
+extern bool pgstat_backend_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header,
 											  TimestampTz ts);
 
@@ -729,7 +757,7 @@ extern void AtEOXact_PgStat_Database(bool isCommit, bool parallel);
 
 extern PgStat_StatDBEntry *pgstat_prep_database_pending(Oid dboid);
 extern void pgstat_reset_database_timestamp(Oid dboid, TimestampTz ts);
-extern bool pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_database_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
@@ -737,7 +765,7 @@ extern void pgstat_database_reset_timestamp_cb(PgStatShared_Common *header, Time
  * Functions in pgstat_function.c
  */
 
-extern bool pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_function_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
@@ -745,9 +773,9 @@ extern void pgstat_function_reset_timestamp_cb(PgStatShared_Common *header, Time
  * Functions in pgstat_io.c
  */
 
-extern void pgstat_flush_io(bool nowait);
+extern void pgstat_flush_io(bool nowait, bool anytime_only);
 
-extern bool pgstat_io_flush_cb(bool nowait);
+extern bool pgstat_io_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_io_init_shmem_cb(void *stats);
 extern void pgstat_io_reset_all_cb(TimestampTz ts);
 extern void pgstat_io_snapshot_cb(void);
@@ -762,7 +790,7 @@ extern void AtEOSubXact_PgStat_Relations(PgStat_SubXactStatus *xact_state, bool
 extern void AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 
-extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
@@ -809,7 +837,7 @@ extern PgStatShared_Common *pgstat_init_entry(PgStat_Kind kind,
  * Functions in pgstat_slru.c
  */
 
-extern bool pgstat_slru_flush_cb(bool nowait);
+extern bool pgstat_slru_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_slru_init_shmem_cb(void *stats);
 extern void pgstat_slru_reset_all_cb(TimestampTz ts);
 extern void pgstat_slru_snapshot_cb(void);
@@ -820,7 +848,7 @@ extern void pgstat_slru_snapshot_cb(void);
  */
 
 extern void pgstat_wal_init_backend_cb(void);
-extern bool pgstat_wal_flush_cb(bool nowait);
+extern bool pgstat_wal_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_wal_init_shmem_cb(void *stats);
 extern void pgstat_wal_reset_all_cb(TimestampTz ts);
 extern void pgstat_wal_snapshot_cb(void);
@@ -830,7 +858,7 @@ extern void pgstat_wal_snapshot_cb(void);
  * Functions in pgstat_subscription.c
  */
 
-extern bool pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_subscription_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h
index 0965b590b34..10723bb664c 100644
--- a/src/include/utils/timeout.h
+++ b/src/include/utils/timeout.h
@@ -35,6 +35,7 @@ typedef enum TimeoutId
 	IDLE_SESSION_TIMEOUT,
 	IDLE_STATS_UPDATE_TIMEOUT,
 	CLIENT_CONNECTION_CHECK_TIMEOUT,
+	ANYTIME_STATS_UPDATE_TIMEOUT,
 	STARTUP_PROGRESS_TIMEOUT,
 	/* First user-definable timeout reason */
 	USER_TIMEOUT,
diff --git a/src/test/modules/test_custom_stats/test_custom_var_stats.c b/src/test/modules/test_custom_stats/test_custom_var_stats.c
index da28afbd929..4c207611236 100644
--- a/src/test/modules/test_custom_stats/test_custom_var_stats.c
+++ b/src/test/modules/test_custom_stats/test_custom_var_stats.c
@@ -84,7 +84,7 @@ static dsa_area *custom_stats_description_dsa = NULL;
 
 /* Flush callback: merge pending stats into shared memory */
 static bool test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref,
-												   bool nowait);
+												   bool nowait, bool anytime_only);
 
 /* Serialization callback: write auxiliary entry data */
 static void test_custom_stats_var_to_serialized_data(const PgStat_HashKey *key,
@@ -151,7 +151,7 @@ _PG_init(void)
  * Returns false only if nowait=true and lock acquisition fails.
  */
 static bool
-test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref, bool nowait)
+test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_StatCustomVarEntry *pending_entry;
 	PgStatShared_CustomVarEntry *shared_entry;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 241945734ec..1dbc4b96f51 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2271,6 +2271,7 @@ PgStat_Counter
 PgStat_EntryRef
 PgStat_EntryRefHashEntry
 PgStat_FetchConsistency
+PgStat_FlushMode
 PgStat_FunctionCallUsage
 PgStat_FunctionCounts
 PgStat_HashKey
-- 
2.34.1


--2MEBAGW8+kohXisi
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v11-0002-Add-anytime-flush-tests-for-custom-stats.patch"



^ permalink  raw  reply  [nested|flat] 12+ messages in thread

* [PATCH v1 1/3] Add pgstat_report_anytime_stat() for periodic stats flushing
@ 2026-01-05 09:41 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-05 09:41 UTC (permalink / raw)

Long running transactions can accumulate significant statistics (WAL, IO, ...)
that remain unflushed until the transaction ends. This delays visibility of
resource usage in monitoring views like pg_stat_io and pg_stat_wal.

This commit introduces pgstat_report_anytime_stat(), which flushes
non transactional statistics even inside active transactions. A new timeout
handler fires every second to call this function, ensuring timely stats visibility
without waiting for transaction completion.

Implementation details:

- Add PgStat_FlushBehavior enum to classify stats kinds:
  * FLUSH_ANYTIME: Stats that can always be flushed (WAL, IO, ...)
  * FLUSH_AT_TXN_BOUNDARY: Stats requiring transaction boundaries

- Modify pgstat_flush_pending_entries() and pgstat_flush_fixed_stats()
  to accept a boolean anytime_only parameter:
  * When false: flushes all stats (existing behavior)
  * When true: flushes only FLUSH_ANYTIME stats and skips FLUSH_AT_TXN_BOUNDARY stats

- Register ANYTIME_STATS_UPDATE_TIMEOUT that fires every 1 second, calling
pgstat_report_anytime_stat(false)

The force parameter in pgstat_report_anytime_stat() is currently unused (always
called with force=false) but reserved for future use cases requiring immediate
flushing.
---
 src/backend/tcop/postgres.c         |  18 +++++
 src/backend/utils/activity/pgstat.c | 119 ++++++++++++++++++++++++----
 src/backend/utils/init/globals.c    |   1 +
 src/backend/utils/init/postinit.c   |  15 ++++
 src/include/miscadmin.h             |   1 +
 src/include/pgstat.h                |   4 +
 src/include/utils/pgstat_internal.h |  11 +++
 src/include/utils/timeout.h         |   1 +
 src/tools/pgindent/typedefs.list    |   1 +
 9 files changed, 154 insertions(+), 17 deletions(-)
   9.7% src/backend/tcop/
  70.2% src/backend/utils/activity/
   9.3% src/backend/utils/init/
   6.0% src/include/utils/
   4.3% src/include/

diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index e54bf1e760f..6a91543f80a 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -3530,6 +3530,24 @@ ProcessInterrupts(void)
 		pgstat_report_stat(true);
 	}
 
+	/*
+	 * Flush stats outside of transaction boundary if the timeout fired.
+	 * Unlike transactional stats, these can be flushed even inside a running
+	 * transaction.
+	 */
+	if (AnytimeStatsUpdateTimeoutPending)
+	{
+		AnytimeStatsUpdateTimeoutPending = false;
+
+		/* Skip if completely idle */
+		if (!DoingCommandRead || IsTransactionOrTransactionBlock())
+			pgstat_report_anytime_stat(false);
+
+		/* Schedule next timeout */
+		enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT,
+							 PGSTAT_ANYTIME_FLUSH_INTERVAL);
+	}
+
 	if (ProcSignalBarrierPending)
 		ProcessProcSignalBarrier();
 
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 11bb71cad5a..f7942e47475 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -187,7 +187,8 @@ static void pgstat_init_snapshot_fixed(void);
 
 static void pgstat_reset_after_failure(void);
 
-static bool pgstat_flush_pending_entries(bool nowait);
+static bool pgstat_flush_pending_entries(bool nowait, bool anytime_only);
+static bool pgstat_flush_fixed_stats(bool nowait, bool anytime_only);
 
 static void pgstat_prep_snapshot(void);
 static void pgstat_build_snapshot(void);
@@ -288,6 +289,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_database entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -305,6 +307,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Relation),
 		.shared_data_off = offsetof(PgStatShared_Relation, stats),
@@ -321,6 +324,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Function),
 		.shared_data_off = offsetof(PgStatShared_Function, stats),
@@ -336,6 +340,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_AT_TXN_BOUNDARY,
 
 		.accessed_across_databases = true,
 
@@ -353,6 +358,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_subscription_stats entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -370,6 +376,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = false,
+		.flush_behavior = FLUSH_ANYTIME,
 
 		.accessed_across_databases = true,
 
@@ -388,6 +395,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, archiver),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, archiver),
@@ -404,6 +412,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, bgwriter),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, bgwriter),
@@ -420,6 +429,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, checkpointer),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, checkpointer),
@@ -436,6 +446,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
@@ -453,6 +464,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, slru),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, slru),
@@ -470,6 +482,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, wal),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, wal),
@@ -775,23 +788,11 @@ pgstat_report_stat(bool force)
 	partial_flush = false;
 
 	/* flush of variable-numbered stats tracked in pending entries list */
-	partial_flush |= pgstat_flush_pending_entries(nowait);
+	partial_flush |= pgstat_flush_pending_entries(nowait, false);
 
 	/* flush of other stats kinds */
 	if (pgstat_report_fixed)
-	{
-		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;
-
-			partial_flush |= kind_info->flush_static_cb(nowait);
-		}
-	}
+		partial_flush |= pgstat_flush_fixed_stats(nowait, false);
 
 	last_flush = now;
 
@@ -1345,9 +1346,14 @@ pgstat_delete_pending_entry(PgStat_EntryRef *entry_ref)
 
 /*
  * Flush out pending variable-numbered stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME entries.
+ * This is safe to call inside transactions.
+ *
+ * If anytime_only is false, flushes all entries.
  */
 static bool
-pgstat_flush_pending_entries(bool nowait)
+pgstat_flush_pending_entries(bool nowait, bool anytime_only)
 {
 	bool		have_pending = false;
 	dlist_node *cur = NULL;
@@ -1377,6 +1383,20 @@ pgstat_flush_pending_entries(bool nowait)
 		Assert(!kind_info->fixed_amount);
 		Assert(kind_info->flush_pending_cb != NULL);
 
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_behavior == FLUSH_AT_TXN_BOUNDARY)
+		{
+			have_pending = true;
+
+			if (dlist_has_next(&pgStatPending, cur))
+				next = dlist_next_node(&pgStatPending, cur);
+			else
+				next = NULL;
+
+			cur = next;
+			continue;
+		}
+
 		/* flush the stats, if possible */
 		did_flush = kind_info->flush_pending_cb(entry_ref, nowait);
 
@@ -1397,11 +1417,42 @@ pgstat_flush_pending_entries(bool nowait)
 		cur = next;
 	}
 
-	Assert(dlist_is_empty(&pgStatPending) == !have_pending);
+	/*
+	 * When in anytime_only mode, the list may not be empty because
+	 * FLUSH_AT_TXN_BOUNDARY entries were skipped.
+	 */
+	Assert(!anytime_only || dlist_is_empty(&pgStatPending) == !have_pending);
 
 	return have_pending;
 }
 
+/*
+ * Flush fixed-amount stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME stats (safe inside transactions).
+ * If anytime_only is false, flushes all stats with flush_static_cb.
+ */
+static bool
+pgstat_flush_fixed_stats(bool nowait, bool anytime_only)
+{
+	bool		partial_flush = false;
+
+	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 || !kind_info->flush_static_cb)
+			continue;
+
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_behavior == FLUSH_AT_TXN_BOUNDARY)
+			continue;
+
+		partial_flush |= kind_info->flush_static_cb(nowait);
+	}
+
+	return partial_flush;
+}
 
 /* ------------------------------------------------------------
  * Helper / infrastructure functions
@@ -2119,3 +2170,37 @@ assign_stats_fetch_consistency(int newval, void *extra)
 	if (pgstat_fetch_consistency != newval)
 		force_stats_snapshot_clear = true;
 }
+
+/*
+ * Flush non-transactional stats
+ *
+ * This is safe to call even inside a transaction. It only flushes stats
+ * kinds marked as FLUSH_ANYTIME.
+ *
+ * This allows long running transactions to report activity without waiting
+ * for transaction to finish.
+ */
+void
+pgstat_report_anytime_stat(bool force)
+{
+	bool		nowait = !force;
+
+	pgstat_assert_is_up();
+
+	/*
+	 * Exit if no pending stats at all. This avoids unnecessary work when
+	 * backends are idle or in sessions without stats accumulation.
+	 *
+	 * Note: This check isn't precise as there might be only transactional
+	 * stats pending, which we'll skip during the flush. However, maintaining
+	 * precise tracking would add complexity that does not seem worth it from
+	 * a performance point of view (no noticeable performance regression has
+	 * been observed with the current implementation).
+	 */
+	if (dlist_is_empty(&pgStatPending) && !pgstat_report_fixed)
+		return;
+
+	/* Flush stats outside of transaction boundary */
+	pgstat_flush_pending_entries(nowait, true);
+	pgstat_flush_fixed_stats(nowait, true);
+}
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 36ad708b360..ad44826c39e 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -40,6 +40,7 @@ volatile sig_atomic_t IdleSessionTimeoutPending = false;
 volatile sig_atomic_t ProcSignalBarrierPending = false;
 volatile sig_atomic_t LogMemoryContextPending = false;
 volatile sig_atomic_t IdleStatsUpdateTimeoutPending = false;
+volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending = false;
 volatile uint32 InterruptHoldoffCount = 0;
 volatile uint32 QueryCancelHoldoffCount = 0;
 volatile uint32 CritSectionCount = 0;
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 3f401faf3de..cb0f6aecad1 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -82,6 +82,7 @@ static void TransactionTimeoutHandler(void);
 static void IdleSessionTimeoutHandler(void);
 static void IdleStatsUpdateTimeoutHandler(void);
 static void ClientCheckTimeoutHandler(void);
+static void AnytimeStatsUpdateTimeoutHandler(void);
 static bool ThereIsAtLeastOneRole(void);
 static void process_startup_options(Port *port, bool am_superuser);
 static void process_settings(Oid databaseid, Oid roleid);
@@ -765,6 +766,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 		RegisterTimeout(CLIENT_CONNECTION_CHECK_TIMEOUT, ClientCheckTimeoutHandler);
 		RegisterTimeout(IDLE_STATS_UPDATE_TIMEOUT,
 						IdleStatsUpdateTimeoutHandler);
+		RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT,
+						AnytimeStatsUpdateTimeoutHandler);
+		enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_ANYTIME_FLUSH_INTERVAL);
 	}
 
 	/*
@@ -1446,3 +1450,14 @@ ThereIsAtLeastOneRole(void)
 
 	return result;
 }
+
+/*
+ * Timeout handler for flushing non-transactional stats.
+ */
+static void
+AnytimeStatsUpdateTimeoutHandler(void)
+{
+	AnytimeStatsUpdateTimeoutPending = true;
+	InterruptPending = true;
+	SetLatch(MyLatch);
+}
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index db559b39c4d..8aeb9628871 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -96,6 +96,7 @@ extern PGDLLIMPORT volatile sig_atomic_t IdleSessionTimeoutPending;
 extern PGDLLIMPORT volatile sig_atomic_t ProcSignalBarrierPending;
 extern PGDLLIMPORT volatile sig_atomic_t LogMemoryContextPending;
 extern PGDLLIMPORT volatile sig_atomic_t IdleStatsUpdateTimeoutPending;
+extern PGDLLIMPORT volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending;
 
 extern PGDLLIMPORT volatile sig_atomic_t CheckClientConnectionPending;
 extern PGDLLIMPORT volatile sig_atomic_t ClientConnectionLost;
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index fff7ecc2533..86e65397614 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -35,6 +35,9 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/* When to call pgstat_report_anytime_stat() again */
+#define PGSTAT_ANYTIME_FLUSH_INTERVAL       1000
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -533,6 +536,7 @@ extern void pgstat_initialize(void);
 
 /* Functions called from backends */
 extern long pgstat_report_stat(bool force);
+extern void pgstat_report_anytime_stat(bool force);
 extern void pgstat_force_next_flush(void);
 
 extern void pgstat_reset_counters(void);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..02f4f13fc0f 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -224,6 +224,14 @@ typedef struct PgStat_SubXactStatus
 	PgStat_TableXactStatus *first;	/* head of list for this subxact */
 } PgStat_SubXactStatus;
 
+/*
+ * Flush behavior for statistics kinds.
+ */
+typedef enum PgStat_FlushBehavior
+{
+	FLUSH_ANYTIME,				/* All fields can flush anytime */
+	FLUSH_AT_TXN_BOUNDARY,		/* All fields need transaction boundary */
+} PgStat_FlushBehavior;
 
 /*
  * Metadata for a specific kind of statistics.
@@ -251,6 +259,9 @@ typedef struct PgStat_KindInfo
 	 */
 	bool		track_entry_count:1;
 
+	/* Flush behavior */
+	PgStat_FlushBehavior flush_behavior;
+
 	/*
 	 * The size of an entry in the shared stats hash table (pointed to by
 	 * PgStatShared_HashEntry->body).  For fixed-numbered statistics, this is
diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h
index 0965b590b34..10723bb664c 100644
--- a/src/include/utils/timeout.h
+++ b/src/include/utils/timeout.h
@@ -35,6 +35,7 @@ typedef enum TimeoutId
 	IDLE_SESSION_TIMEOUT,
 	IDLE_STATS_UPDATE_TIMEOUT,
 	CLIENT_CONNECTION_CHECK_TIMEOUT,
+	ANYTIME_STATS_UPDATE_TIMEOUT,
 	STARTUP_PROGRESS_TIMEOUT,
 	/* First user-definable timeout reason */
 	USER_TIMEOUT,
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 09e7f1d420e..9aabb325f16 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2261,6 +2261,7 @@ PgStat_Counter
 PgStat_EntryRef
 PgStat_EntryRefHashEntry
 PgStat_FetchConsistency
+PgStat_FlushBehavior
 PgStat_FunctionCallUsage
 PgStat_FunctionCounts
 PgStat_HashKey
-- 
2.34.1


--tjEWjIIwfNIHQLgt
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Remove-useless-calls-to-flush-some-stats.patch"



^ permalink  raw  reply  [nested|flat] 12+ messages in thread

* [PATCH v2 1/3] Add pgstat_report_anytime_stat() for periodic stats flushing
@ 2026-01-05 09:41 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-05 09:41 UTC (permalink / raw)

Long running transactions can accumulate significant statistics (WAL, IO, ...)
that remain unflushed until the transaction ends. This delays visibility of
resource usage in monitoring views like pg_stat_io and pg_stat_wal.

This commit introduces pgstat_report_anytime_stat(), which flushes
non transactional statistics even inside active transactions. A new timeout
handler fires every second to call this function, ensuring timely stats visibility
without waiting for transaction completion.

Implementation details:

- Add PgStat_FlushBehavior enum to classify stats kinds:
  * FLUSH_ANYTIME: Stats that can always be flushed (WAL, IO, ...)
  * FLUSH_AT_TXN_BOUNDARY: Stats requiring transaction boundaries

- Modify pgstat_flush_pending_entries() and pgstat_flush_fixed_stats()
  to accept a boolean anytime_only parameter:
  * When false: flushes all stats (existing behavior)
  * When true: flushes only FLUSH_ANYTIME stats and skips FLUSH_AT_TXN_BOUNDARY stats

- Register ANYTIME_STATS_UPDATE_TIMEOUT that fires every 1 second, calling
pgstat_report_anytime_stat(false)

The force parameter in pgstat_report_anytime_stat() is currently unused (always
called with force=false) but reserved for future use cases requiring immediate
flushing.
---
 src/backend/tcop/postgres.c         |  16 ++++
 src/backend/utils/activity/pgstat.c | 113 ++++++++++++++++++++++++----
 src/backend/utils/init/globals.c    |   1 +
 src/backend/utils/init/postinit.c   |  15 ++++
 src/include/miscadmin.h             |   1 +
 src/include/pgstat.h                |   4 +
 src/include/utils/pgstat_internal.h |  13 ++++
 src/include/utils/timeout.h         |   1 +
 src/tools/pgindent/typedefs.list    |   1 +
 9 files changed, 149 insertions(+), 16 deletions(-)
   8.2% src/backend/tcop/
  69.3% src/backend/utils/activity/
   9.7% src/backend/utils/init/
   7.7% src/include/utils/
   4.5% src/include/

diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index e54bf1e760f..9c4a9078ee0 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -3530,6 +3530,22 @@ ProcessInterrupts(void)
 		pgstat_report_stat(true);
 	}
 
+	/*
+	 * Flush stats outside of transaction boundary if the timeout fired.
+	 * Unlike transactional stats, these can be flushed even inside a running
+	 * transaction.
+	 */
+	if (AnytimeStatsUpdateTimeoutPending)
+	{
+		AnytimeStatsUpdateTimeoutPending = false;
+
+		pgstat_report_anytime_stat(false);
+
+		/* Schedule next timeout */
+		enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT,
+							 PGSTAT_ANYTIME_FLUSH_INTERVAL);
+	}
+
 	if (ProcSignalBarrierPending)
 		ProcessProcSignalBarrier();
 
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 11bb71cad5a..0f45a7d165e 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -187,7 +187,8 @@ static void pgstat_init_snapshot_fixed(void);
 
 static void pgstat_reset_after_failure(void);
 
-static bool pgstat_flush_pending_entries(bool nowait);
+static bool pgstat_flush_pending_entries(bool nowait, bool anytime_only);
+static bool pgstat_flush_fixed_stats(bool nowait, bool anytime_only);
 
 static void pgstat_prep_snapshot(void);
 static void pgstat_build_snapshot(void);
@@ -288,6 +289,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_database entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -305,6 +307,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Relation),
 		.shared_data_off = offsetof(PgStatShared_Relation, stats),
@@ -321,6 +324,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Function),
 		.shared_data_off = offsetof(PgStatShared_Function, stats),
@@ -336,6 +340,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_AT_TXN_BOUNDARY,
 
 		.accessed_across_databases = true,
 
@@ -353,6 +358,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_subscription_stats entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -370,6 +376,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = false,
+		.flush_behavior = FLUSH_ANYTIME,
 
 		.accessed_across_databases = true,
 
@@ -388,6 +395,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, archiver),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, archiver),
@@ -404,6 +412,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, bgwriter),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, bgwriter),
@@ -420,6 +429,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, checkpointer),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, checkpointer),
@@ -436,6 +446,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
@@ -453,6 +464,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, slru),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, slru),
@@ -470,6 +482,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_behavior = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, wal),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, wal),
@@ -775,23 +788,11 @@ pgstat_report_stat(bool force)
 	partial_flush = false;
 
 	/* flush of variable-numbered stats tracked in pending entries list */
-	partial_flush |= pgstat_flush_pending_entries(nowait);
+	partial_flush |= pgstat_flush_pending_entries(nowait, false);
 
 	/* flush of other stats kinds */
 	if (pgstat_report_fixed)
-	{
-		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;
-
-			partial_flush |= kind_info->flush_static_cb(nowait);
-		}
-	}
+		partial_flush |= pgstat_flush_fixed_stats(nowait, false);
 
 	last_flush = now;
 
@@ -1345,9 +1346,14 @@ pgstat_delete_pending_entry(PgStat_EntryRef *entry_ref)
 
 /*
  * Flush out pending variable-numbered stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME entries.
+ * This is safe to call inside transactions.
+ *
+ * If anytime_only is false, flushes all entries.
  */
 static bool
-pgstat_flush_pending_entries(bool nowait)
+pgstat_flush_pending_entries(bool nowait, bool anytime_only)
 {
 	bool		have_pending = false;
 	dlist_node *cur = NULL;
@@ -1377,6 +1383,20 @@ pgstat_flush_pending_entries(bool nowait)
 		Assert(!kind_info->fixed_amount);
 		Assert(kind_info->flush_pending_cb != NULL);
 
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_behavior == FLUSH_AT_TXN_BOUNDARY)
+		{
+			have_pending = true;
+
+			if (dlist_has_next(&pgStatPending, cur))
+				next = dlist_next_node(&pgStatPending, cur);
+			else
+				next = NULL;
+
+			cur = next;
+			continue;
+		}
+
 		/* flush the stats, if possible */
 		did_flush = kind_info->flush_pending_cb(entry_ref, nowait);
 
@@ -1397,11 +1417,42 @@ pgstat_flush_pending_entries(bool nowait)
 		cur = next;
 	}
 
+	/*
+	 * When in anytime_only mode, the list may not be empty because
+	 * FLUSH_AT_TXN_BOUNDARY entries were skipped.
+	 */
 	Assert(dlist_is_empty(&pgStatPending) == !have_pending);
 
 	return have_pending;
 }
 
+/*
+ * Flush fixed-amount stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME stats (safe inside transactions).
+ * If anytime_only is false, flushes all stats with flush_static_cb.
+ */
+static bool
+pgstat_flush_fixed_stats(bool nowait, bool anytime_only)
+{
+	bool		partial_flush = false;
+
+	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 || !kind_info->flush_static_cb)
+			continue;
+
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_behavior == FLUSH_AT_TXN_BOUNDARY)
+			continue;
+
+		partial_flush |= kind_info->flush_static_cb(nowait);
+	}
+
+	return partial_flush;
+}
 
 /* ------------------------------------------------------------
  * Helper / infrastructure functions
@@ -2119,3 +2170,33 @@ assign_stats_fetch_consistency(int newval, void *extra)
 	if (pgstat_fetch_consistency != newval)
 		force_stats_snapshot_clear = true;
 }
+
+/*
+ * Flushes only FLUSH_ANYTIME stats using non-blocking locks. Transactional
+ * stats (FLUSH_AT_TXN_BOUNDARY) remain pending until transaction boundary.
+ * Safe to call inside transactions.
+ */
+void
+pgstat_report_anytime_stat(bool force)
+{
+	bool		nowait = !force;
+
+	pgstat_assert_is_up();
+
+	/*
+	 * Exit if no pending stats at all. This avoids unnecessary work when
+	 * backends are idle or in sessions without stats accumulation.
+	 *
+	 * Note: This check isn't precise as there might be only transactional
+	 * stats pending, which we'll skip during the flush. However, maintaining
+	 * precise tracking would add complexity that does not seem worth it from
+	 * a performance point of view (no noticeable performance regression has
+	 * been observed with the current implementation).
+	 */
+	if (dlist_is_empty(&pgStatPending) && !pgstat_report_fixed)
+		return;
+
+	/* Flush stats outside of transaction boundary */
+	pgstat_flush_pending_entries(nowait, true);
+	pgstat_flush_fixed_stats(nowait, true);
+}
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 36ad708b360..ad44826c39e 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -40,6 +40,7 @@ volatile sig_atomic_t IdleSessionTimeoutPending = false;
 volatile sig_atomic_t ProcSignalBarrierPending = false;
 volatile sig_atomic_t LogMemoryContextPending = false;
 volatile sig_atomic_t IdleStatsUpdateTimeoutPending = false;
+volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending = false;
 volatile uint32 InterruptHoldoffCount = 0;
 volatile uint32 QueryCancelHoldoffCount = 0;
 volatile uint32 CritSectionCount = 0;
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 3f401faf3de..cb0f6aecad1 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -82,6 +82,7 @@ static void TransactionTimeoutHandler(void);
 static void IdleSessionTimeoutHandler(void);
 static void IdleStatsUpdateTimeoutHandler(void);
 static void ClientCheckTimeoutHandler(void);
+static void AnytimeStatsUpdateTimeoutHandler(void);
 static bool ThereIsAtLeastOneRole(void);
 static void process_startup_options(Port *port, bool am_superuser);
 static void process_settings(Oid databaseid, Oid roleid);
@@ -765,6 +766,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 		RegisterTimeout(CLIENT_CONNECTION_CHECK_TIMEOUT, ClientCheckTimeoutHandler);
 		RegisterTimeout(IDLE_STATS_UPDATE_TIMEOUT,
 						IdleStatsUpdateTimeoutHandler);
+		RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT,
+						AnytimeStatsUpdateTimeoutHandler);
+		enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_ANYTIME_FLUSH_INTERVAL);
 	}
 
 	/*
@@ -1446,3 +1450,14 @@ ThereIsAtLeastOneRole(void)
 
 	return result;
 }
+
+/*
+ * Timeout handler for flushing non-transactional stats.
+ */
+static void
+AnytimeStatsUpdateTimeoutHandler(void)
+{
+	AnytimeStatsUpdateTimeoutPending = true;
+	InterruptPending = true;
+	SetLatch(MyLatch);
+}
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index db559b39c4d..8aeb9628871 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -96,6 +96,7 @@ extern PGDLLIMPORT volatile sig_atomic_t IdleSessionTimeoutPending;
 extern PGDLLIMPORT volatile sig_atomic_t ProcSignalBarrierPending;
 extern PGDLLIMPORT volatile sig_atomic_t LogMemoryContextPending;
 extern PGDLLIMPORT volatile sig_atomic_t IdleStatsUpdateTimeoutPending;
+extern PGDLLIMPORT volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending;
 
 extern PGDLLIMPORT volatile sig_atomic_t CheckClientConnectionPending;
 extern PGDLLIMPORT volatile sig_atomic_t ClientConnectionLost;
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index fff7ecc2533..86e65397614 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -35,6 +35,9 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/* When to call pgstat_report_anytime_stat() again */
+#define PGSTAT_ANYTIME_FLUSH_INTERVAL       1000
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -533,6 +536,7 @@ extern void pgstat_initialize(void);
 
 /* Functions called from backends */
 extern long pgstat_report_stat(bool force);
+extern void pgstat_report_anytime_stat(bool force);
 extern void pgstat_force_next_flush(void);
 
 extern void pgstat_reset_counters(void);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..63feae640d1 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -224,6 +224,16 @@ typedef struct PgStat_SubXactStatus
 	PgStat_TableXactStatus *first;	/* head of list for this subxact */
 } PgStat_SubXactStatus;
 
+/*
+ * Flush behavior for statistics kinds.
+ */
+typedef enum PgStat_FlushBehavior
+{
+	FLUSH_ANYTIME,				/* All fields can be flushed anytime,
+								 * including within transactions */
+	FLUSH_AT_TXN_BOUNDARY,		/* All fields can only be flushed at
+								 * transaction boundary */
+} PgStat_FlushBehavior;
 
 /*
  * Metadata for a specific kind of statistics.
@@ -251,6 +261,9 @@ typedef struct PgStat_KindInfo
 	 */
 	bool		track_entry_count:1;
 
+	/* Flush behavior */
+	PgStat_FlushBehavior flush_behavior;
+
 	/*
 	 * The size of an entry in the shared stats hash table (pointed to by
 	 * PgStatShared_HashEntry->body).  For fixed-numbered statistics, this is
diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h
index 0965b590b34..10723bb664c 100644
--- a/src/include/utils/timeout.h
+++ b/src/include/utils/timeout.h
@@ -35,6 +35,7 @@ typedef enum TimeoutId
 	IDLE_SESSION_TIMEOUT,
 	IDLE_STATS_UPDATE_TIMEOUT,
 	CLIENT_CONNECTION_CHECK_TIMEOUT,
+	ANYTIME_STATS_UPDATE_TIMEOUT,
 	STARTUP_PROGRESS_TIMEOUT,
 	/* First user-definable timeout reason */
 	USER_TIMEOUT,
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 3f3a888fd0e..610b35a9b31 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2268,6 +2268,7 @@ PgStat_Counter
 PgStat_EntryRef
 PgStat_EntryRefHashEntry
 PgStat_FetchConsistency
+PgStat_FlushBehavior
 PgStat_FunctionCallUsage
 PgStat_FunctionCounts
 PgStat_HashKey
-- 
2.34.1


--OFsrIl+bjhifp5hk
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Remove-useless-calls-to-flush-some-stats.patch"



^ permalink  raw  reply  [nested|flat] 12+ messages in thread

* [PATCH v7 1/5] Add pgstat_report_anytime_stat() for periodic stats flushing
@ 2026-01-05 09:41 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-05 09:41 UTC (permalink / raw)

Long running transactions can accumulate significant statistics (WAL, IO, ...)
that remain unflushed until the transaction ends. This delays visibility of
resource usage in monitoring views like pg_stat_io and pg_stat_wal and produces
spikes when flushed.

This commit introduces pgstat_report_anytime_stat(), which flushes
non transactional statistics even inside active transactions. A new timeout
handler fires every second (if enabled while adding pending stats) to call this
function, ensuring timely stats visibility without waiting for transaction completion.

Implementation details:

- Add PgStat_FlushMode enum to classify stats kinds:
  * FLUSH_ANYTIME: Stats that can always be flushed (WAL, IO, ...)
  * FLUSH_AT_TXN_BOUNDARY: Stats requiring transaction boundaries

- Modify pgstat_flush_pending_entries() and pgstat_flush_fixed_stats()
  to accept a boolean anytime_only parameter:
  * When false: flushes all stats (existing behavior)
  * When true: flushes only FLUSH_ANYTIME stats and skips FLUSH_AT_TXN_BOUNDARY stats

- The flush_pending_cb and flush_static_cb callbacks now receive an anytime_only
boolean parameter. Most of the time it's not used (except for assertions), but it's
preparatory work for moving the relations stats to anytime (without introducin
a new callback).

- Add pgstat_schedule_anytime_update() macro to schedule the next anytime flush,
relying on PGSTAT_MIN_INTERVAL

The force parameter in pgstat_report_anytime_stat() is currently unused (always
called with force=false) but reserved for future use cases requiring immediate
flushing.
---
 src/backend/access/transam/xlog.c             |   6 +
 src/backend/postmaster/bgwriter.c             |   9 +-
 src/backend/postmaster/checkpointer.c         |  10 +-
 src/backend/postmaster/startup.c              |   2 +
 src/backend/postmaster/walsummarizer.c        |   9 +-
 src/backend/postmaster/walwriter.c            |   9 +-
 src/backend/replication/walreceiver.c         |   9 +-
 src/backend/replication/walsender.c           |   8 +-
 src/backend/tcop/postgres.c                   |  12 ++
 src/backend/utils/activity/pgstat.c           | 112 ++++++++++++++----
 src/backend/utils/activity/pgstat_backend.c   |  13 +-
 src/backend/utils/activity/pgstat_bgwriter.c  |   2 +-
 .../utils/activity/pgstat_checkpointer.c      |   2 +-
 src/backend/utils/activity/pgstat_database.c  |   2 +-
 src/backend/utils/activity/pgstat_function.c  |   4 +-
 src/backend/utils/activity/pgstat_io.c        |  10 +-
 src/backend/utils/activity/pgstat_relation.c  |  12 +-
 src/backend/utils/activity/pgstat_slru.c      |   6 +-
 .../utils/activity/pgstat_subscription.c      |   4 +-
 src/backend/utils/activity/pgstat_wal.c       |  10 +-
 src/backend/utils/init/globals.c              |   1 +
 src/backend/utils/init/postinit.c             |   3 +
 src/include/miscadmin.h                       |   1 +
 src/include/pgstat.h                          |  16 +++
 src/include/utils/pgstat_internal.h           |  52 ++++++--
 src/include/utils/timeout.h                   |   1 +
 .../test_custom_stats/test_custom_var_stats.c |   4 +-
 src/tools/pgindent/typedefs.list              |   1 +
 28 files changed, 264 insertions(+), 66 deletions(-)
  10.8% src/backend/postmaster/
   6.0% src/backend/replication/
  50.7% src/backend/utils/activity/
   6.0% src/backend/
  19.3% src/include/utils/
   5.6% src/include/

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..d01b11c7470 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -1085,6 +1085,9 @@ XLogInsertRecord(XLogRecData *rdata,
 		pgWalUsage.wal_fpi += num_fpi;
 		pgWalUsage.wal_fpi_bytes += fpi_bytes;
 
+		/* Schedule next anytime stats update timeout */
+		pgstat_schedule_anytime_update();
+
 		/* Required for the flush of pending stats WAL data */
 		pgstat_report_fixed = true;
 	}
@@ -2066,6 +2069,9 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic)
 					pgWalUsage.wal_buffers_full++;
 					TRACE_POSTGRESQL_WAL_BUFFER_WRITE_DIRTY_DONE();
 
+					/* Schedule next anytime stats update timeout */
+					pgstat_schedule_anytime_update();
+
 					/*
 					 * Required for the flush of pending stats WAL data, per
 					 * update of pgWalUsage.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 0956bd39a85..059c601c3b8 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -49,7 +49,9 @@
 #include "storage/smgr.h"
 #include "storage/standby.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 /*
@@ -103,7 +105,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN);
@@ -113,6 +115,11 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * We just started, assume there has been either a shutdown or
 	 * end-of-recovery snapshot.
diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c
index e03c19123bc..e11c4b099c8 100644
--- a/src/backend/postmaster/checkpointer.c
+++ b/src/backend/postmaster/checkpointer.c
@@ -66,8 +66,9 @@
 #include "utils/acl.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
-
+#include "utils/timeout.h"
 
 /*----------
  * Shared memory area for communication between checkpointer and backends
@@ -215,7 +216,7 @@ CheckpointerMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, ReqShutdownXLOG);
 	pqsignal(SIGTERM, SIG_IGN); /* ignore SIGTERM */
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SignalHandlerForShutdownRequest);
@@ -225,6 +226,11 @@ CheckpointerMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * Initialize so that first time-driven event happens at the correct time.
 	 */
diff --git a/src/backend/postmaster/startup.c b/src/backend/postmaster/startup.c
index cdbe53dd262..4954fe425b7 100644
--- a/src/backend/postmaster/startup.c
+++ b/src/backend/postmaster/startup.c
@@ -32,6 +32,7 @@
 #include "storage/standby.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timeout.h"
 
 
@@ -245,6 +246,7 @@ StartupProcessMain(const void *startup_data, size_t startup_data_len)
 	RegisterTimeout(STANDBY_DEADLOCK_TIMEOUT, StandbyDeadLockHandler);
 	RegisterTimeout(STANDBY_TIMEOUT, StandbyTimeoutHandler);
 	RegisterTimeout(STANDBY_LOCK_TIMEOUT, StandbyLockTimeoutHandler);
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
 
 	/*
 	 * Unblock signals (they were blocked when the postmaster forked us)
diff --git a/src/backend/postmaster/walsummarizer.c b/src/backend/postmaster/walsummarizer.c
index 2d8f57099fd..9f8ef8159d1 100644
--- a/src/backend/postmaster/walsummarizer.c
+++ b/src/backend/postmaster/walsummarizer.c
@@ -48,6 +48,8 @@
 #include "storage/shmem.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 #include "utils/wait_event.h"
 
 /*
@@ -249,7 +251,7 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SignalHandlerForShutdownRequest);
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN); /* not used */
@@ -271,6 +273,11 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * If an exception is encountered, processing resumes here.
 	 */
diff --git a/src/backend/postmaster/walwriter.c b/src/backend/postmaster/walwriter.c
index 23e79a32345..ded0f250288 100644
--- a/src/backend/postmaster/walwriter.c
+++ b/src/backend/postmaster/walwriter.c
@@ -61,7 +61,9 @@
 #include "storage/smgr.h"
 #include "utils/hsearch.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
+#include "utils/timeout.h"
 
 
 /*
@@ -106,7 +108,7 @@ WalWriterMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SignalHandlerForShutdownRequest);
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN); /* not used */
@@ -116,6 +118,11 @@ WalWriterMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * Create a memory context that we will do all our work in.  We do this so
 	 * that we can reset the context during error recovery and thereby avoid
diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index 10e64a7d1f4..11b7c114d3b 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -77,7 +77,9 @@
 #include "utils/builtins.h"
 #include "utils/guc.h"
 #include "utils/pg_lsn.h"
+#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 
@@ -252,7 +254,7 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);
 	pqsignal(SIGTERM, die);		/* request shutdown */
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN);
@@ -260,6 +262,11 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/* Load the libpq-specific functions */
 	load_file("libpqwalreceiver", false);
 	if (WalReceiverFunctions == NULL)
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 2cde8ebc729..a7214d0dc6f 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -1987,8 +1987,8 @@ WalSndWaitForWal(XLogRecPtr loc)
 		if (TimestampDifferenceExceeds(last_flush, now,
 									   WALSENDER_STATS_FLUSH_INTERVAL))
 		{
-			pgstat_flush_io(false);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+			pgstat_flush_io(false, true);
+			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 			last_flush = now;
 		}
 
@@ -3016,8 +3016,8 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			if (TimestampDifferenceExceeds(last_flush, now,
 										   WALSENDER_STATS_FLUSH_INTERVAL))
 			{
-				pgstat_flush_io(false);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+				pgstat_flush_io(false, true);
+				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 				last_flush = now;
 			}
 
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index 21de158adbb..2089de782d5 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -3564,6 +3564,18 @@ ProcessInterrupts(void)
 		pgstat_report_stat(true);
 	}
 
+	/*
+	 * Flush stats outside of transaction boundary if the timeout fired.
+	 * Unlike transactional stats, these can be flushed even inside a running
+	 * transaction.
+	 */
+	if (AnytimeStatsUpdateTimeoutPending)
+	{
+		AnytimeStatsUpdateTimeoutPending = false;
+
+		pgstat_report_anytime_stat(false);
+	}
+
 	if (ProcSignalBarrierPending)
 		ProcessProcSignalBarrier();
 
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 11bb71cad5a..a4ff64dc5ce 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -112,6 +112,7 @@
 #include "utils/guc_hooks.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 
@@ -122,8 +123,6 @@
  * ----------
  */
 
-/* minimum interval non-forced stats flushes.*/
-#define PGSTAT_MIN_INTERVAL			1000
 /* how long until to block flushing pending stats updates */
 #define PGSTAT_MAX_INTERVAL			60000
 /* when to call pgstat_report_stat() again, even when idle */
@@ -187,7 +186,8 @@ static void pgstat_init_snapshot_fixed(void);
 
 static void pgstat_reset_after_failure(void);
 
-static bool pgstat_flush_pending_entries(bool nowait);
+static bool pgstat_flush_pending_entries(bool nowait, bool anytime_only);
+static bool pgstat_flush_fixed_stats(bool nowait, bool anytime_only);
 
 static void pgstat_prep_snapshot(void);
 static void pgstat_build_snapshot(void);
@@ -288,6 +288,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_database entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -305,6 +306,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Relation),
 		.shared_data_off = offsetof(PgStatShared_Relation, stats),
@@ -321,6 +323,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Function),
 		.shared_data_off = offsetof(PgStatShared_Function, stats),
@@ -336,6 +339,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.accessed_across_databases = true,
 
@@ -353,6 +357,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_subscription_stats entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -370,6 +375,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = false,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.accessed_across_databases = true,
 
@@ -436,6 +442,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
@@ -453,6 +460,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, slru),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, slru),
@@ -470,6 +478,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, wal),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, wal),
@@ -775,23 +784,11 @@ pgstat_report_stat(bool force)
 	partial_flush = false;
 
 	/* flush of variable-numbered stats tracked in pending entries list */
-	partial_flush |= pgstat_flush_pending_entries(nowait);
+	partial_flush |= pgstat_flush_pending_entries(nowait, false);
 
 	/* flush of other stats kinds */
 	if (pgstat_report_fixed)
-	{
-		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;
-
-			partial_flush |= kind_info->flush_static_cb(nowait);
-		}
-	}
+		partial_flush |= pgstat_flush_fixed_stats(nowait, false);
 
 	last_flush = now;
 
@@ -1293,7 +1290,8 @@ pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid, uint64 objid, bool *creat
 
 	if (entry_ref->pending == NULL)
 	{
-		size_t		entrysize = pgstat_get_kind_info(kind)->pending_size;
+		const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
+		size_t		entrysize = kind_info->pending_size;
 
 		Assert(entrysize != (size_t) -1);
 
@@ -1345,9 +1343,14 @@ pgstat_delete_pending_entry(PgStat_EntryRef *entry_ref)
 
 /*
  * Flush out pending variable-numbered stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME entries.
+ * This is safe to call inside transactions.
+ *
+ * If anytime_only is false, flushes all entries.
  */
 static bool
-pgstat_flush_pending_entries(bool nowait)
+pgstat_flush_pending_entries(bool nowait, bool anytime_only)
 {
 	bool		have_pending = false;
 	dlist_node *cur = NULL;
@@ -1377,8 +1380,22 @@ pgstat_flush_pending_entries(bool nowait)
 		Assert(!kind_info->fixed_amount);
 		Assert(kind_info->flush_pending_cb != NULL);
 
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+		{
+			have_pending = true;
+
+			if (dlist_has_next(&pgStatPending, cur))
+				next = dlist_next_node(&pgStatPending, cur);
+			else
+				next = NULL;
+
+			cur = next;
+			continue;
+		}
+
 		/* flush the stats, if possible */
-		did_flush = kind_info->flush_pending_cb(entry_ref, nowait);
+		did_flush = kind_info->flush_pending_cb(entry_ref, nowait, anytime_only);
 
 		Assert(did_flush || nowait);
 
@@ -1402,6 +1419,33 @@ pgstat_flush_pending_entries(bool nowait)
 	return have_pending;
 }
 
+/*
+ * Flush fixed-amount stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME stats (safe inside transactions).
+ * If anytime_only is false, flushes all stats with flush_static_cb.
+ */
+static bool
+pgstat_flush_fixed_stats(bool nowait, bool anytime_only)
+{
+	bool		partial_flush = false;
+
+	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 || !kind_info->flush_static_cb)
+			continue;
+
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+			continue;
+
+		partial_flush |= kind_info->flush_static_cb(nowait, anytime_only);
+	}
+
+	return partial_flush;
+}
 
 /* ------------------------------------------------------------
  * Helper / infrastructure functions
@@ -2119,3 +2163,31 @@ assign_stats_fetch_consistency(int newval, void *extra)
 	if (pgstat_fetch_consistency != newval)
 		force_stats_snapshot_clear = true;
 }
+
+/*
+ * Flushes only FLUSH_ANYTIME stats using non-blocking locks. Transactional
+ * stats (FLUSH_AT_TXN_BOUNDARY) remain pending until transaction boundary.
+ * Safe to call inside transactions.
+ */
+void
+pgstat_report_anytime_stat(bool force)
+{
+	bool		nowait = !force;
+
+	pgstat_assert_is_up();
+
+	/* Flush stats outside of transaction boundary */
+	pgstat_flush_pending_entries(nowait, true);
+	pgstat_flush_fixed_stats(nowait, true);
+}
+
+/*
+ * Timeout handler for flushing anytime stats.
+ */
+void
+AnytimeStatsUpdateTimeoutHandler(void)
+{
+	AnytimeStatsUpdateTimeoutPending = true;
+	InterruptPending = true;
+	SetLatch(MyLatch);
+}
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index f2f8d3ff75f..b09316d3ab3 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -31,6 +31,7 @@
 #include "storage/procarray.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 
 /*
  * Backend statistics counts waiting to be flushed out. These counters may be
@@ -66,6 +67,9 @@ pgstat_count_backend_io_op_time(IOObject io_object, IOContext io_context,
 	INSTR_TIME_ADD(PendingBackendStats.pending_io.pending_times[io_object][io_context][io_op],
 				   io_time);
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	backend_has_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -82,6 +86,9 @@ pgstat_count_backend_io_op(IOObject io_object, IOContext io_context,
 	PendingBackendStats.pending_io.counts[io_object][io_context][io_op] += cnt;
 	PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	backend_has_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -268,7 +275,7 @@ pgstat_flush_backend_entry_wal(PgStat_EntryRef *entry_ref)
  * if some statistics could not be flushed due to lock contention.
  */
 bool
-pgstat_flush_backend(bool nowait, bits32 flags)
+pgstat_flush_backend(bool nowait, bits32 flags, bool anytime_only)
 {
 	PgStat_EntryRef *entry_ref;
 	bool		has_pending_data = false;
@@ -311,9 +318,9 @@ pgstat_flush_backend(bool nowait, bits32 flags)
  * If some stats could not be flushed due to lock contention, return true.
  */
 bool
-pgstat_backend_flush_cb(bool nowait)
+pgstat_backend_flush_cb(bool nowait, bool anytime_only)
 {
-	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL);
+	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL, anytime_only);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_bgwriter.c b/src/backend/utils/activity/pgstat_bgwriter.c
index ed2fd801189..1c5f0c3ec40 100644
--- a/src/backend/utils/activity/pgstat_bgwriter.c
+++ b/src/backend/utils/activity/pgstat_bgwriter.c
@@ -61,7 +61,7 @@ pgstat_report_bgwriter(void)
 	/*
 	 * Report IO statistics
 	 */
-	pgstat_flush_io(false);
+	pgstat_flush_io(false, true);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_checkpointer.c b/src/backend/utils/activity/pgstat_checkpointer.c
index 1f70194b7a7..2d89a082464 100644
--- a/src/backend/utils/activity/pgstat_checkpointer.c
+++ b/src/backend/utils/activity/pgstat_checkpointer.c
@@ -68,7 +68,7 @@ pgstat_report_checkpointer(void)
 	/*
 	 * Report IO statistics
 	 */
-	pgstat_flush_io(false);
+	pgstat_flush_io(false, true);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_database.c b/src/backend/utils/activity/pgstat_database.c
index 933dcb5cae5..8e86df60461 100644
--- a/src/backend/utils/activity/pgstat_database.c
+++ b/src/backend/utils/activity/pgstat_database.c
@@ -435,7 +435,7 @@ pgstat_reset_database_timestamp(Oid dboid, TimestampTz ts)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStatShared_Database *sharedent;
 	PgStat_StatDBEntry *pendingent;
diff --git a/src/backend/utils/activity/pgstat_function.c b/src/backend/utils/activity/pgstat_function.c
index e6b84283c6c..5ba4958382f 100644
--- a/src/backend/utils/activity/pgstat_function.c
+++ b/src/backend/utils/activity/pgstat_function.c
@@ -190,11 +190,13 @@ pgstat_end_function_usage(PgStat_FunctionCallUsage *fcu, bool finalize)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_FunctionCounts *localent;
 	PgStatShared_Function *shfuncent;
 
+	Assert(!anytime_only);
+
 	localent = (PgStat_FunctionCounts *) entry_ref->pending;
 	shfuncent = (PgStatShared_Function *) entry_ref->shared_stats;
 
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 28de24538dc..7cd32900236 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -19,6 +19,7 @@
 #include "executor/instrument.h"
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
@@ -79,6 +80,9 @@ pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op,
 	/* Add the per-backend counts */
 	pgstat_count_backend_io_op(io_object, io_context, io_op, cnt, bytes);
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	have_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -172,9 +176,9 @@ pgstat_fetch_stat_io(void)
  * Simpler wrapper of pgstat_io_flush_cb()
  */
 void
-pgstat_flush_io(bool nowait)
+pgstat_flush_io(bool nowait, bool anytime_only)
 {
-	(void) pgstat_io_flush_cb(nowait);
+	(void) pgstat_io_flush_cb(nowait, anytime_only);
 }
 
 /*
@@ -186,7 +190,7 @@ pgstat_flush_io(bool nowait)
  * acquired. Otherwise, return false.
  */
 bool
-pgstat_io_flush_cb(bool nowait)
+pgstat_io_flush_cb(bool nowait, bool anytime_only)
 {
 	LWLock	   *bktype_lock;
 	PgStat_BktypeIO *bktype_shstats;
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..04d21483d93 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -267,8 +267,8 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	 * is done -- which will likely vacuum many relations -- or until the
 	 * VACUUM command has processed all tables and committed.
 	 */
-	pgstat_flush_io(false);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(false, true);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -362,8 +362,8 @@ pgstat_report_analyze(Relation rel,
 	pgstat_unlock_entry(entry_ref);
 
 	/* see pgstat_report_vacuum() */
-	pgstat_flush_io(false);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(false, true);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -812,7 +812,7 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
  * entry when successfully flushing.
  */
 bool
-pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	Oid			dboid;
 	PgStat_TableStatus *lstats; /* pending stats entry  */
@@ -820,6 +820,8 @@ pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
 	PgStat_StatTabEntry *tabentry;	/* table entry of shared stats */
 	PgStat_StatDBEntry *dbentry;	/* pending database entry */
 
+	Assert(!anytime_only);
+
 	dboid = entry_ref->shared_entry->key.dboid;
 	lstats = (PgStat_TableStatus *) entry_ref->pending;
 	shtabstats = (PgStatShared_Relation *) entry_ref->shared_stats;
diff --git a/src/backend/utils/activity/pgstat_slru.c b/src/backend/utils/activity/pgstat_slru.c
index 2190f388eae..bf8a4d58673 100644
--- a/src/backend/utils/activity/pgstat_slru.c
+++ b/src/backend/utils/activity/pgstat_slru.c
@@ -19,6 +19,7 @@
 
 #include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
+#include "utils/timeout.h"
 
 
 static inline PgStat_SLRUStats *get_slru_entry(int slru_idx);
@@ -139,7 +140,7 @@ pgstat_get_slru_index(const char *name)
  * acquired. Otherwise return false.
  */
 bool
-pgstat_slru_flush_cb(bool nowait)
+pgstat_slru_flush_cb(bool nowait, bool anytime_only)
 {
 	PgStatShared_SLRU *stats_shmem = &pgStatLocal.shmem->slru;
 	int			i;
@@ -223,6 +224,9 @@ get_slru_entry(int slru_idx)
 
 	Assert((slru_idx >= 0) && (slru_idx < SLRU_NUM_ELEMENTS));
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	have_slrustats = true;
 	pgstat_report_fixed = true;
 
diff --git a/src/backend/utils/activity/pgstat_subscription.c b/src/backend/utils/activity/pgstat_subscription.c
index 500b1899188..c4614817966 100644
--- a/src/backend/utils/activity/pgstat_subscription.c
+++ b/src/backend/utils/activity/pgstat_subscription.c
@@ -116,11 +116,13 @@ pgstat_fetch_stat_subscription(Oid subid)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_BackendSubEntry *localent;
 	PgStatShared_Subscription *shsubent;
 
+	Assert(!anytime_only);
+
 	localent = (PgStat_BackendSubEntry *) entry_ref->pending;
 	shsubent = (PgStatShared_Subscription *) entry_ref->shared_stats;
 
diff --git a/src/backend/utils/activity/pgstat_wal.c b/src/backend/utils/activity/pgstat_wal.c
index 183e0a7a97b..2c2f3f10e10 100644
--- a/src/backend/utils/activity/pgstat_wal.c
+++ b/src/backend/utils/activity/pgstat_wal.c
@@ -51,12 +51,12 @@ pgstat_report_wal(bool force)
 	nowait = !force;
 
 	/* flush wal stats */
-	(void) pgstat_wal_flush_cb(nowait);
-	pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_WAL);
+	(void) pgstat_wal_flush_cb(nowait, true);
+	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_WAL, true);
 
 	/* flush IO stats */
-	pgstat_flush_io(nowait);
-	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(nowait, true);
+	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -88,7 +88,7 @@ pgstat_wal_have_pending(void)
  * acquired. Otherwise return false.
  */
 bool
-pgstat_wal_flush_cb(bool nowait)
+pgstat_wal_flush_cb(bool nowait, bool anytime_only)
 {
 	PgStatShared_Wal *stats_shmem = &pgStatLocal.shmem->wal;
 	WalUsage	wal_usage_diff = {0};
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 36ad708b360..ad44826c39e 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -40,6 +40,7 @@ volatile sig_atomic_t IdleSessionTimeoutPending = false;
 volatile sig_atomic_t ProcSignalBarrierPending = false;
 volatile sig_atomic_t LogMemoryContextPending = false;
 volatile sig_atomic_t IdleStatsUpdateTimeoutPending = false;
+volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending = false;
 volatile uint32 InterruptHoldoffCount = 0;
 volatile uint32 QueryCancelHoldoffCount = 0;
 volatile uint32 CritSectionCount = 0;
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index b59e08605cc..eeeac1bf39a 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -64,6 +64,7 @@
 #include "utils/injection_point.h"
 #include "utils/memutils.h"
 #include "utils/pg_locale.h"
+#include "utils/pgstat_internal.h"
 #include "utils/portal.h"
 #include "utils/ps_status.h"
 #include "utils/snapmgr.h"
@@ -773,6 +774,8 @@ InitPostgres(const char *in_dbname, Oid dboid,
 		RegisterTimeout(CLIENT_CONNECTION_CHECK_TIMEOUT, ClientCheckTimeoutHandler);
 		RegisterTimeout(IDLE_STATS_UPDATE_TIMEOUT,
 						IdleStatsUpdateTimeoutHandler);
+		RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT,
+						AnytimeStatsUpdateTimeoutHandler);
 	}
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index f16f35659b9..84e698da214 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -96,6 +96,7 @@ extern PGDLLIMPORT volatile sig_atomic_t IdleSessionTimeoutPending;
 extern PGDLLIMPORT volatile sig_atomic_t ProcSignalBarrierPending;
 extern PGDLLIMPORT volatile sig_atomic_t LogMemoryContextPending;
 extern PGDLLIMPORT volatile sig_atomic_t IdleStatsUpdateTimeoutPending;
+extern PGDLLIMPORT volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending;
 
 extern PGDLLIMPORT volatile sig_atomic_t CheckClientConnectionPending;
 extern PGDLLIMPORT volatile sig_atomic_t ClientConnectionLost;
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index fff7ecc2533..b340a680614 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -35,6 +35,9 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/* Minimum interval non-forced stats flushes */
+#define PGSTAT_MIN_INTERVAL	1000
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -533,8 +536,21 @@ extern void pgstat_initialize(void);
 
 /* Functions called from backends */
 extern long pgstat_report_stat(bool force);
+extern void pgstat_report_anytime_stat(bool force);
 extern void pgstat_force_next_flush(void);
 
+/*
+ * Schedule the next anytime stats update timeout.
+ *
+ * This should be called whenever accumulating statistics that support
+ * FLUSH_ANYTIME flushing mode.
+ */
+#define pgstat_schedule_anytime_update()												\
+	do {																				\
+		if (IsUnderPostmaster && !get_timeout_active(ANYTIME_STATS_UPDATE_TIMEOUT))		\
+			enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);	\
+	} while (0)
+
 extern void pgstat_reset_counters(void);
 extern void pgstat_reset(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_reset_of_kind(PgStat_Kind kind);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..607f4255268 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -224,6 +224,19 @@ typedef struct PgStat_SubXactStatus
 	PgStat_TableXactStatus *first;	/* head of list for this subxact */
 } PgStat_SubXactStatus;
 
+/*
+ * Flush mode for statistics kinds.
+ *
+ * FLUSH_AT_TXN_BOUNDARY has to be the first because we want it to be the
+ * default value.
+ */
+typedef enum PgStat_FlushMode
+{
+	FLUSH_AT_TXN_BOUNDARY,		/* All fields can only be flushed at
+								 * transaction boundary */
+	FLUSH_ANYTIME,				/* All fields can be flushed anytime,
+								 * including within transactions */
+} PgStat_FlushMode;
 
 /*
  * Metadata for a specific kind of statistics.
@@ -251,6 +264,16 @@ typedef struct PgStat_KindInfo
 	 */
 	bool		track_entry_count:1;
 
+	/*
+	 * The mode of when to flush stats. See PgStat_FlushMode for more details.
+	 *
+	 * This member only has meaning for statistics kinds that accumulate
+	 * pending stats and use flush callbacks. For kinds that write directly to
+	 * shared memory (e.g., archiver, bgwriter, checkpointer), this member has
+	 * no effect.
+	 */
+	PgStat_FlushMode flush_mode;
+
 	/*
 	 * The size of an entry in the shared stats hash table (pointed to by
 	 * PgStatShared_HashEntry->body).  For fixed-numbered statistics, this is
@@ -297,8 +320,10 @@ typedef struct PgStat_KindInfo
 	 * For variable-numbered stats: flush pending stats. Required if pending
 	 * data is used. See flush_static_cb when dealing with stats data that
 	 * that cannot use PgStat_EntryRef->pending.
+	 *
+	 * The anytime_only parameter indicates whether this is an anytime flush.
 	 */
-	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait);
+	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait, bool anytime_only);
 
 	/*
 	 * For variable-numbered stats: delete pending stats. Optional.
@@ -366,8 +391,10 @@ typedef struct PgStat_KindInfo
 	 *
 	 * "pgstat_report_fixed" needs to be set to trigger the flush of pending
 	 * stats.
+	 *
+	 * The anytime_only parameter indicates whether this is an anytime flush.
 	 */
-	bool		(*flush_static_cb) (bool nowait);
+	bool		(*flush_static_cb) (bool nowait, bool anytime_only);
 
 	/*
 	 * For fixed-numbered statistics: Reset All.
@@ -677,6 +704,7 @@ extern PgStat_EntryRef *pgstat_fetch_pending_entry(PgStat_Kind kind,
 
 extern void *pgstat_fetch_entry(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_snapshot_fixed(PgStat_Kind kind);
+extern void AnytimeStatsUpdateTimeoutHandler(void);
 
 
 /*
@@ -696,8 +724,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL)
 
-extern bool pgstat_flush_backend(bool nowait, bits32 flags);
-extern bool pgstat_backend_flush_cb(bool nowait);
+extern bool pgstat_flush_backend(bool nowait, bits32 flags, bool anytime_only);
+extern bool pgstat_backend_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header,
 											  TimestampTz ts);
 
@@ -729,7 +757,7 @@ extern void AtEOXact_PgStat_Database(bool isCommit, bool parallel);
 
 extern PgStat_StatDBEntry *pgstat_prep_database_pending(Oid dboid);
 extern void pgstat_reset_database_timestamp(Oid dboid, TimestampTz ts);
-extern bool pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_database_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
@@ -737,7 +765,7 @@ extern void pgstat_database_reset_timestamp_cb(PgStatShared_Common *header, Time
  * Functions in pgstat_function.c
  */
 
-extern bool pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_function_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
@@ -745,9 +773,9 @@ extern void pgstat_function_reset_timestamp_cb(PgStatShared_Common *header, Time
  * Functions in pgstat_io.c
  */
 
-extern void pgstat_flush_io(bool nowait);
+extern void pgstat_flush_io(bool nowait, bool anytime_only);
 
-extern bool pgstat_io_flush_cb(bool nowait);
+extern bool pgstat_io_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_io_init_shmem_cb(void *stats);
 extern void pgstat_io_reset_all_cb(TimestampTz ts);
 extern void pgstat_io_snapshot_cb(void);
@@ -762,7 +790,7 @@ extern void AtEOSubXact_PgStat_Relations(PgStat_SubXactStatus *xact_state, bool
 extern void AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 
-extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
@@ -809,7 +837,7 @@ extern PgStatShared_Common *pgstat_init_entry(PgStat_Kind kind,
  * Functions in pgstat_slru.c
  */
 
-extern bool pgstat_slru_flush_cb(bool nowait);
+extern bool pgstat_slru_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_slru_init_shmem_cb(void *stats);
 extern void pgstat_slru_reset_all_cb(TimestampTz ts);
 extern void pgstat_slru_snapshot_cb(void);
@@ -820,7 +848,7 @@ extern void pgstat_slru_snapshot_cb(void);
  */
 
 extern void pgstat_wal_init_backend_cb(void);
-extern bool pgstat_wal_flush_cb(bool nowait);
+extern bool pgstat_wal_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_wal_init_shmem_cb(void *stats);
 extern void pgstat_wal_reset_all_cb(TimestampTz ts);
 extern void pgstat_wal_snapshot_cb(void);
@@ -830,7 +858,7 @@ extern void pgstat_wal_snapshot_cb(void);
  * Functions in pgstat_subscription.c
  */
 
-extern bool pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_subscription_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h
index 0965b590b34..10723bb664c 100644
--- a/src/include/utils/timeout.h
+++ b/src/include/utils/timeout.h
@@ -35,6 +35,7 @@ typedef enum TimeoutId
 	IDLE_SESSION_TIMEOUT,
 	IDLE_STATS_UPDATE_TIMEOUT,
 	CLIENT_CONNECTION_CHECK_TIMEOUT,
+	ANYTIME_STATS_UPDATE_TIMEOUT,
 	STARTUP_PROGRESS_TIMEOUT,
 	/* First user-definable timeout reason */
 	USER_TIMEOUT,
diff --git a/src/test/modules/test_custom_stats/test_custom_var_stats.c b/src/test/modules/test_custom_stats/test_custom_var_stats.c
index 64a8fe63cce..bc0b5d6e0eb 100644
--- a/src/test/modules/test_custom_stats/test_custom_var_stats.c
+++ b/src/test/modules/test_custom_stats/test_custom_var_stats.c
@@ -83,7 +83,7 @@ static dsa_area *custom_stats_description_dsa = NULL;
 
 /* Flush callback: merge pending stats into shared memory */
 static bool test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref,
-												   bool nowait);
+												   bool nowait, bool anytime_only);
 
 /* Serialization callback: write auxiliary entry data */
 static void test_custom_stats_var_to_serialized_data(const PgStat_HashKey *key,
@@ -150,7 +150,7 @@ _PG_init(void)
  * Returns false only if nowait=true and lock acquisition fails.
  */
 static bool
-test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref, bool nowait)
+test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_StatCustomVarEntry *pending_entry;
 	PgStatShared_CustomVarEntry *shared_entry;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 241945734ec..1dbc4b96f51 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2271,6 +2271,7 @@ PgStat_Counter
 PgStat_EntryRef
 PgStat_EntryRefHashEntry
 PgStat_FetchConsistency
+PgStat_FlushMode
 PgStat_FunctionCallUsage
 PgStat_FunctionCounts
 PgStat_HashKey
-- 
2.34.1


--C2xzVbxFmVrP7k6O
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v7-0002-Add-anytime-flush-tests-for-custom-stats.patch"



^ permalink  raw  reply  [nested|flat] 12+ messages in thread

* [PATCH v10 1/5] Add pgstat_report_anytime_stat() for periodic stats flushing
@ 2026-01-05 09:41 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-05 09:41 UTC (permalink / raw)

Long running transactions can accumulate significant statistics (WAL, IO, ...)
that remain unflushed until the transaction ends. This delays visibility of
resource usage in monitoring views like pg_stat_io and pg_stat_wal and produces
spikes when flushed.

This commit introduces pgstat_report_anytime_stat(), which flushes
non transactional statistics even inside active transactions. A new timeout
handler fires every second (if enabled while adding pending stats) to call this
function, ensuring timely stats visibility without waiting for transaction completion.

Implementation details:

- Add PgStat_FlushMode enum to classify stats kinds:
  * FLUSH_ANYTIME: Stats that can always be flushed (WAL, IO, ...)
  * FLUSH_AT_TXN_BOUNDARY: Stats requiring transaction boundaries

- Modify pgstat_flush_pending_entries() and pgstat_flush_fixed_stats()
  to accept a boolean anytime_only parameter:
  * When false: flushes all stats (existing behavior)
  * When true: flushes only FLUSH_ANYTIME stats and skips FLUSH_AT_TXN_BOUNDARY stats

- The flush_pending_cb and flush_static_cb callbacks now receive an anytime_only
boolean parameter. Most of the time it's not used (except for assertions), but it's
preparatory work for moving the relations stats to anytime (without introducin
a new callback).

- Add pgstat_schedule_anytime_update() macro to schedule the next anytime flush,
relying on PGSTAT_MIN_INTERVAL

The force parameter in pgstat_report_anytime_stat() is currently unused (always
called with force=false) but reserved for future use cases requiring immediate
flushing.
---
 src/backend/access/transam/xlog.c             |   6 +
 src/backend/postmaster/bgwriter.c             |   9 +-
 src/backend/postmaster/checkpointer.c         |  10 +-
 src/backend/postmaster/startup.c              |   2 +
 src/backend/postmaster/walsummarizer.c        |   9 +-
 src/backend/postmaster/walwriter.c            |   9 +-
 src/backend/replication/walreceiver.c         |   9 +-
 src/backend/replication/walsender.c           |   8 +-
 src/backend/tcop/postgres.c                   |  12 ++
 src/backend/utils/activity/pgstat.c           | 121 +++++++++++++++---
 src/backend/utils/activity/pgstat_backend.c   |  13 +-
 src/backend/utils/activity/pgstat_bgwriter.c  |   2 +-
 .../utils/activity/pgstat_checkpointer.c      |   2 +-
 src/backend/utils/activity/pgstat_database.c  |   2 +-
 src/backend/utils/activity/pgstat_function.c  |   4 +-
 src/backend/utils/activity/pgstat_io.c        |  10 +-
 src/backend/utils/activity/pgstat_relation.c  |  12 +-
 src/backend/utils/activity/pgstat_slru.c      |   6 +-
 .../utils/activity/pgstat_subscription.c      |   4 +-
 src/backend/utils/activity/pgstat_wal.c       |  10 +-
 src/backend/utils/init/globals.c              |   1 +
 src/backend/utils/init/postinit.c             |   3 +
 src/include/miscadmin.h                       |   1 +
 src/include/pgstat.h                          |  22 ++++
 src/include/utils/pgstat_internal.h           |  52 ++++++--
 src/include/utils/timeout.h                   |   1 +
 .../test_custom_stats/test_custom_var_stats.c |   4 +-
 src/tools/pgindent/typedefs.list              |   1 +
 28 files changed, 279 insertions(+), 66 deletions(-)
  10.5% src/backend/postmaster/
   5.8% src/backend/replication/
  51.0% src/backend/utils/activity/
   5.8% src/backend/
  18.7% src/include/utils/
   6.6% src/include/

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13cce9b49f1..cf29fc91f70 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -1085,6 +1085,9 @@ XLogInsertRecord(XLogRecData *rdata,
 		pgWalUsage.wal_fpi += num_fpi;
 		pgWalUsage.wal_fpi_bytes += fpi_bytes;
 
+		/* Schedule next anytime stats update timeout */
+		pgstat_schedule_anytime_update();
+
 		/* Required for the flush of pending stats WAL data */
 		pgstat_report_fixed = true;
 	}
@@ -2066,6 +2069,9 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic)
 					pgWalUsage.wal_buffers_full++;
 					TRACE_POSTGRESQL_WAL_BUFFER_WRITE_DIRTY_DONE();
 
+					/* Schedule next anytime stats update timeout */
+					pgstat_schedule_anytime_update();
+
 					/*
 					 * Required for the flush of pending stats WAL data, per
 					 * update of pgWalUsage.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 0956bd39a85..059c601c3b8 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -49,7 +49,9 @@
 #include "storage/smgr.h"
 #include "storage/standby.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 /*
@@ -103,7 +105,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN);
@@ -113,6 +115,11 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * We just started, assume there has been either a shutdown or
 	 * end-of-recovery snapshot.
diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c
index e03c19123bc..e11c4b099c8 100644
--- a/src/backend/postmaster/checkpointer.c
+++ b/src/backend/postmaster/checkpointer.c
@@ -66,8 +66,9 @@
 #include "utils/acl.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
-
+#include "utils/timeout.h"
 
 /*----------
  * Shared memory area for communication between checkpointer and backends
@@ -215,7 +216,7 @@ CheckpointerMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, ReqShutdownXLOG);
 	pqsignal(SIGTERM, SIG_IGN); /* ignore SIGTERM */
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SignalHandlerForShutdownRequest);
@@ -225,6 +226,11 @@ CheckpointerMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * Initialize so that first time-driven event happens at the correct time.
 	 */
diff --git a/src/backend/postmaster/startup.c b/src/backend/postmaster/startup.c
index cdbe53dd262..4954fe425b7 100644
--- a/src/backend/postmaster/startup.c
+++ b/src/backend/postmaster/startup.c
@@ -32,6 +32,7 @@
 #include "storage/standby.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timeout.h"
 
 
@@ -245,6 +246,7 @@ StartupProcessMain(const void *startup_data, size_t startup_data_len)
 	RegisterTimeout(STANDBY_DEADLOCK_TIMEOUT, StandbyDeadLockHandler);
 	RegisterTimeout(STANDBY_TIMEOUT, StandbyTimeoutHandler);
 	RegisterTimeout(STANDBY_LOCK_TIMEOUT, StandbyLockTimeoutHandler);
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
 
 	/*
 	 * Unblock signals (they were blocked when the postmaster forked us)
diff --git a/src/backend/postmaster/walsummarizer.c b/src/backend/postmaster/walsummarizer.c
index 742137edad6..f1bae9d23d6 100644
--- a/src/backend/postmaster/walsummarizer.c
+++ b/src/backend/postmaster/walsummarizer.c
@@ -48,6 +48,8 @@
 #include "storage/shmem.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 #include "utils/wait_event.h"
 
 /*
@@ -246,7 +248,7 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);	/* no query to cancel */
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN); /* not used */
@@ -268,6 +270,11 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * If an exception is encountered, processing resumes here.
 	 */
diff --git a/src/backend/postmaster/walwriter.c b/src/backend/postmaster/walwriter.c
index 7c0e2809c17..bcf59227a00 100644
--- a/src/backend/postmaster/walwriter.c
+++ b/src/backend/postmaster/walwriter.c
@@ -61,7 +61,9 @@
 #include "storage/smgr.h"
 #include "utils/hsearch.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
+#include "utils/timeout.h"
 
 
 /*
@@ -103,7 +105,7 @@ WalWriterMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);	/* no query to cancel */
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN); /* not used */
@@ -113,6 +115,11 @@ WalWriterMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * Create a memory context that we will do all our work in.  We do this so
 	 * that we can reset the context during error recovery and thereby avoid
diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index 7c1b8757d7d..aecc7a127e6 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -77,7 +77,9 @@
 #include "utils/builtins.h"
 #include "utils/guc.h"
 #include "utils/pg_lsn.h"
+#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 
@@ -252,7 +254,7 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);
 	pqsignal(SIGTERM, die);		/* request shutdown */
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN);
@@ -260,6 +262,11 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/* Load the libpq-specific functions */
 	load_file("libpqwalreceiver", false);
 	if (WalReceiverFunctions == NULL)
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 2cde8ebc729..a7214d0dc6f 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -1987,8 +1987,8 @@ WalSndWaitForWal(XLogRecPtr loc)
 		if (TimestampDifferenceExceeds(last_flush, now,
 									   WALSENDER_STATS_FLUSH_INTERVAL))
 		{
-			pgstat_flush_io(false);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+			pgstat_flush_io(false, true);
+			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 			last_flush = now;
 		}
 
@@ -3016,8 +3016,8 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			if (TimestampDifferenceExceeds(last_flush, now,
 										   WALSENDER_STATS_FLUSH_INTERVAL))
 			{
-				pgstat_flush_io(false);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+				pgstat_flush_io(false, true);
+				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 				last_flush = now;
 			}
 
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index d01a09dd0c4..8c30efa2443 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -3564,6 +3564,18 @@ ProcessInterrupts(void)
 		pgstat_report_stat(true);
 	}
 
+	/*
+	 * Flush stats outside of transaction boundary if the timeout fired.
+	 * Unlike transactional stats, these can be flushed even inside a running
+	 * transaction.
+	 */
+	if (AnytimeStatsUpdateTimeoutPending)
+	{
+		AnytimeStatsUpdateTimeoutPending = false;
+
+		pgstat_report_anytime_stat(false);
+	}
+
 	if (ProcSignalBarrierPending)
 		ProcessProcSignalBarrier();
 
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 11bb71cad5a..ddd331e2c81 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -108,10 +108,12 @@
 #include "pgstat.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
+#include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "utils/guc_hooks.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 
@@ -122,8 +124,6 @@
  * ----------
  */
 
-/* minimum interval non-forced stats flushes.*/
-#define PGSTAT_MIN_INTERVAL			1000
 /* how long until to block flushing pending stats updates */
 #define PGSTAT_MAX_INTERVAL			60000
 /* when to call pgstat_report_stat() again, even when idle */
@@ -187,7 +187,8 @@ static void pgstat_init_snapshot_fixed(void);
 
 static void pgstat_reset_after_failure(void);
 
-static bool pgstat_flush_pending_entries(bool nowait);
+static bool pgstat_flush_pending_entries(bool nowait, bool anytime_only);
+static bool pgstat_flush_fixed_stats(bool nowait, bool anytime_only);
 
 static void pgstat_prep_snapshot(void);
 static void pgstat_build_snapshot(void);
@@ -218,6 +219,12 @@ PgStat_LocalState pgStatLocal;
  */
 bool		pgstat_report_fixed = false;
 
+/*
+ * Track when there is pending anytime flush to avoid relying on
+ * get_timeout_active() in hot pathes.
+ */
+bool		pgstat_pending_anytime = false;
+
 /* ----------
  * Local data
  *
@@ -288,6 +295,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_database entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -305,6 +313,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Relation),
 		.shared_data_off = offsetof(PgStatShared_Relation, stats),
@@ -321,6 +330,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Function),
 		.shared_data_off = offsetof(PgStatShared_Function, stats),
@@ -336,6 +346,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.accessed_across_databases = true,
 
@@ -353,6 +364,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_subscription_stats entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -370,6 +382,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = false,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.accessed_across_databases = true,
 
@@ -436,6 +449,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
@@ -453,6 +467,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, slru),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, slru),
@@ -470,6 +485,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, wal),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, wal),
@@ -775,23 +791,11 @@ pgstat_report_stat(bool force)
 	partial_flush = false;
 
 	/* flush of variable-numbered stats tracked in pending entries list */
-	partial_flush |= pgstat_flush_pending_entries(nowait);
+	partial_flush |= pgstat_flush_pending_entries(nowait, false);
 
 	/* flush of other stats kinds */
 	if (pgstat_report_fixed)
-	{
-		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;
-
-			partial_flush |= kind_info->flush_static_cb(nowait);
-		}
-	}
+		partial_flush |= pgstat_flush_fixed_stats(nowait, false);
 
 	last_flush = now;
 
@@ -1293,7 +1297,8 @@ pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid, uint64 objid, bool *creat
 
 	if (entry_ref->pending == NULL)
 	{
-		size_t		entrysize = pgstat_get_kind_info(kind)->pending_size;
+		const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
+		size_t		entrysize = kind_info->pending_size;
 
 		Assert(entrysize != (size_t) -1);
 
@@ -1345,9 +1350,14 @@ pgstat_delete_pending_entry(PgStat_EntryRef *entry_ref)
 
 /*
  * Flush out pending variable-numbered stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME entries.
+ * This is safe to call inside transactions.
+ *
+ * If anytime_only is false, flushes all entries.
  */
 static bool
-pgstat_flush_pending_entries(bool nowait)
+pgstat_flush_pending_entries(bool nowait, bool anytime_only)
 {
 	bool		have_pending = false;
 	dlist_node *cur = NULL;
@@ -1377,8 +1387,22 @@ pgstat_flush_pending_entries(bool nowait)
 		Assert(!kind_info->fixed_amount);
 		Assert(kind_info->flush_pending_cb != NULL);
 
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+		{
+			have_pending = true;
+
+			if (dlist_has_next(&pgStatPending, cur))
+				next = dlist_next_node(&pgStatPending, cur);
+			else
+				next = NULL;
+
+			cur = next;
+			continue;
+		}
+
 		/* flush the stats, if possible */
-		did_flush = kind_info->flush_pending_cb(entry_ref, nowait);
+		did_flush = kind_info->flush_pending_cb(entry_ref, nowait, anytime_only);
 
 		Assert(did_flush || nowait);
 
@@ -1402,6 +1426,33 @@ pgstat_flush_pending_entries(bool nowait)
 	return have_pending;
 }
 
+/*
+ * Flush fixed-amount stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME stats (safe inside transactions).
+ * If anytime_only is false, flushes all stats with flush_static_cb.
+ */
+static bool
+pgstat_flush_fixed_stats(bool nowait, bool anytime_only)
+{
+	bool		partial_flush = false;
+
+	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 || !kind_info->flush_static_cb)
+			continue;
+
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+			continue;
+
+		partial_flush |= kind_info->flush_static_cb(nowait, anytime_only);
+	}
+
+	return partial_flush;
+}
 
 /* ------------------------------------------------------------
  * Helper / infrastructure functions
@@ -2119,3 +2170,33 @@ assign_stats_fetch_consistency(int newval, void *extra)
 	if (pgstat_fetch_consistency != newval)
 		force_stats_snapshot_clear = true;
 }
+
+/*
+ * Flushes only FLUSH_ANYTIME stats using non-blocking locks. Transactional
+ * stats (FLUSH_AT_TXN_BOUNDARY) remain pending until transaction boundary.
+ * Safe to call inside transactions.
+ */
+void
+pgstat_report_anytime_stat(bool force)
+{
+	bool		nowait = !force;
+
+	pgstat_assert_is_up();
+
+	/* Flush stats outside of transaction boundary */
+	pgstat_flush_pending_entries(nowait, true);
+	pgstat_flush_fixed_stats(nowait, true);
+
+	pgstat_pending_anytime = false;
+}
+
+/*
+ * Timeout handler for flushing anytime stats.
+ */
+void
+AnytimeStatsUpdateTimeoutHandler(void)
+{
+	AnytimeStatsUpdateTimeoutPending = true;
+	InterruptPending = true;
+	SetLatch(MyLatch);
+}
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index f2f8d3ff75f..b09316d3ab3 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -31,6 +31,7 @@
 #include "storage/procarray.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 
 /*
  * Backend statistics counts waiting to be flushed out. These counters may be
@@ -66,6 +67,9 @@ pgstat_count_backend_io_op_time(IOObject io_object, IOContext io_context,
 	INSTR_TIME_ADD(PendingBackendStats.pending_io.pending_times[io_object][io_context][io_op],
 				   io_time);
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	backend_has_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -82,6 +86,9 @@ pgstat_count_backend_io_op(IOObject io_object, IOContext io_context,
 	PendingBackendStats.pending_io.counts[io_object][io_context][io_op] += cnt;
 	PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	backend_has_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -268,7 +275,7 @@ pgstat_flush_backend_entry_wal(PgStat_EntryRef *entry_ref)
  * if some statistics could not be flushed due to lock contention.
  */
 bool
-pgstat_flush_backend(bool nowait, bits32 flags)
+pgstat_flush_backend(bool nowait, bits32 flags, bool anytime_only)
 {
 	PgStat_EntryRef *entry_ref;
 	bool		has_pending_data = false;
@@ -311,9 +318,9 @@ pgstat_flush_backend(bool nowait, bits32 flags)
  * If some stats could not be flushed due to lock contention, return true.
  */
 bool
-pgstat_backend_flush_cb(bool nowait)
+pgstat_backend_flush_cb(bool nowait, bool anytime_only)
 {
-	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL);
+	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL, anytime_only);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_bgwriter.c b/src/backend/utils/activity/pgstat_bgwriter.c
index ed2fd801189..1c5f0c3ec40 100644
--- a/src/backend/utils/activity/pgstat_bgwriter.c
+++ b/src/backend/utils/activity/pgstat_bgwriter.c
@@ -61,7 +61,7 @@ pgstat_report_bgwriter(void)
 	/*
 	 * Report IO statistics
 	 */
-	pgstat_flush_io(false);
+	pgstat_flush_io(false, true);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_checkpointer.c b/src/backend/utils/activity/pgstat_checkpointer.c
index 1f70194b7a7..2d89a082464 100644
--- a/src/backend/utils/activity/pgstat_checkpointer.c
+++ b/src/backend/utils/activity/pgstat_checkpointer.c
@@ -68,7 +68,7 @@ pgstat_report_checkpointer(void)
 	/*
 	 * Report IO statistics
 	 */
-	pgstat_flush_io(false);
+	pgstat_flush_io(false, true);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_database.c b/src/backend/utils/activity/pgstat_database.c
index 933dcb5cae5..8e86df60461 100644
--- a/src/backend/utils/activity/pgstat_database.c
+++ b/src/backend/utils/activity/pgstat_database.c
@@ -435,7 +435,7 @@ pgstat_reset_database_timestamp(Oid dboid, TimestampTz ts)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStatShared_Database *sharedent;
 	PgStat_StatDBEntry *pendingent;
diff --git a/src/backend/utils/activity/pgstat_function.c b/src/backend/utils/activity/pgstat_function.c
index e6b84283c6c..5ba4958382f 100644
--- a/src/backend/utils/activity/pgstat_function.c
+++ b/src/backend/utils/activity/pgstat_function.c
@@ -190,11 +190,13 @@ pgstat_end_function_usage(PgStat_FunctionCallUsage *fcu, bool finalize)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_FunctionCounts *localent;
 	PgStatShared_Function *shfuncent;
 
+	Assert(!anytime_only);
+
 	localent = (PgStat_FunctionCounts *) entry_ref->pending;
 	shfuncent = (PgStatShared_Function *) entry_ref->shared_stats;
 
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 28de24538dc..7cd32900236 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -19,6 +19,7 @@
 #include "executor/instrument.h"
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
@@ -79,6 +80,9 @@ pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op,
 	/* Add the per-backend counts */
 	pgstat_count_backend_io_op(io_object, io_context, io_op, cnt, bytes);
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	have_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -172,9 +176,9 @@ pgstat_fetch_stat_io(void)
  * Simpler wrapper of pgstat_io_flush_cb()
  */
 void
-pgstat_flush_io(bool nowait)
+pgstat_flush_io(bool nowait, bool anytime_only)
 {
-	(void) pgstat_io_flush_cb(nowait);
+	(void) pgstat_io_flush_cb(nowait, anytime_only);
 }
 
 /*
@@ -186,7 +190,7 @@ pgstat_flush_io(bool nowait)
  * acquired. Otherwise, return false.
  */
 bool
-pgstat_io_flush_cb(bool nowait)
+pgstat_io_flush_cb(bool nowait, bool anytime_only)
 {
 	LWLock	   *bktype_lock;
 	PgStat_BktypeIO *bktype_shstats;
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..04d21483d93 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -267,8 +267,8 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	 * is done -- which will likely vacuum many relations -- or until the
 	 * VACUUM command has processed all tables and committed.
 	 */
-	pgstat_flush_io(false);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(false, true);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -362,8 +362,8 @@ pgstat_report_analyze(Relation rel,
 	pgstat_unlock_entry(entry_ref);
 
 	/* see pgstat_report_vacuum() */
-	pgstat_flush_io(false);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(false, true);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -812,7 +812,7 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
  * entry when successfully flushing.
  */
 bool
-pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	Oid			dboid;
 	PgStat_TableStatus *lstats; /* pending stats entry  */
@@ -820,6 +820,8 @@ pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
 	PgStat_StatTabEntry *tabentry;	/* table entry of shared stats */
 	PgStat_StatDBEntry *dbentry;	/* pending database entry */
 
+	Assert(!anytime_only);
+
 	dboid = entry_ref->shared_entry->key.dboid;
 	lstats = (PgStat_TableStatus *) entry_ref->pending;
 	shtabstats = (PgStatShared_Relation *) entry_ref->shared_stats;
diff --git a/src/backend/utils/activity/pgstat_slru.c b/src/backend/utils/activity/pgstat_slru.c
index 2190f388eae..bf8a4d58673 100644
--- a/src/backend/utils/activity/pgstat_slru.c
+++ b/src/backend/utils/activity/pgstat_slru.c
@@ -19,6 +19,7 @@
 
 #include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
+#include "utils/timeout.h"
 
 
 static inline PgStat_SLRUStats *get_slru_entry(int slru_idx);
@@ -139,7 +140,7 @@ pgstat_get_slru_index(const char *name)
  * acquired. Otherwise return false.
  */
 bool
-pgstat_slru_flush_cb(bool nowait)
+pgstat_slru_flush_cb(bool nowait, bool anytime_only)
 {
 	PgStatShared_SLRU *stats_shmem = &pgStatLocal.shmem->slru;
 	int			i;
@@ -223,6 +224,9 @@ get_slru_entry(int slru_idx)
 
 	Assert((slru_idx >= 0) && (slru_idx < SLRU_NUM_ELEMENTS));
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	have_slrustats = true;
 	pgstat_report_fixed = true;
 
diff --git a/src/backend/utils/activity/pgstat_subscription.c b/src/backend/utils/activity/pgstat_subscription.c
index 3277cf88a4e..6b6eec7578d 100644
--- a/src/backend/utils/activity/pgstat_subscription.c
+++ b/src/backend/utils/activity/pgstat_subscription.c
@@ -117,11 +117,13 @@ pgstat_fetch_stat_subscription(Oid subid)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_BackendSubEntry *localent;
 	PgStatShared_Subscription *shsubent;
 
+	Assert(!anytime_only);
+
 	localent = (PgStat_BackendSubEntry *) entry_ref->pending;
 	shsubent = (PgStatShared_Subscription *) entry_ref->shared_stats;
 
diff --git a/src/backend/utils/activity/pgstat_wal.c b/src/backend/utils/activity/pgstat_wal.c
index 183e0a7a97b..2c2f3f10e10 100644
--- a/src/backend/utils/activity/pgstat_wal.c
+++ b/src/backend/utils/activity/pgstat_wal.c
@@ -51,12 +51,12 @@ pgstat_report_wal(bool force)
 	nowait = !force;
 
 	/* flush wal stats */
-	(void) pgstat_wal_flush_cb(nowait);
-	pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_WAL);
+	(void) pgstat_wal_flush_cb(nowait, true);
+	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_WAL, true);
 
 	/* flush IO stats */
-	pgstat_flush_io(nowait);
-	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(nowait, true);
+	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -88,7 +88,7 @@ pgstat_wal_have_pending(void)
  * acquired. Otherwise return false.
  */
 bool
-pgstat_wal_flush_cb(bool nowait)
+pgstat_wal_flush_cb(bool nowait, bool anytime_only)
 {
 	PgStatShared_Wal *stats_shmem = &pgStatLocal.shmem->wal;
 	WalUsage	wal_usage_diff = {0};
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 36ad708b360..ad44826c39e 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -40,6 +40,7 @@ volatile sig_atomic_t IdleSessionTimeoutPending = false;
 volatile sig_atomic_t ProcSignalBarrierPending = false;
 volatile sig_atomic_t LogMemoryContextPending = false;
 volatile sig_atomic_t IdleStatsUpdateTimeoutPending = false;
+volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending = false;
 volatile uint32 InterruptHoldoffCount = 0;
 volatile uint32 QueryCancelHoldoffCount = 0;
 volatile uint32 CritSectionCount = 0;
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index b59e08605cc..eeeac1bf39a 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -64,6 +64,7 @@
 #include "utils/injection_point.h"
 #include "utils/memutils.h"
 #include "utils/pg_locale.h"
+#include "utils/pgstat_internal.h"
 #include "utils/portal.h"
 #include "utils/ps_status.h"
 #include "utils/snapmgr.h"
@@ -773,6 +774,8 @@ InitPostgres(const char *in_dbname, Oid dboid,
 		RegisterTimeout(CLIENT_CONNECTION_CHECK_TIMEOUT, ClientCheckTimeoutHandler);
 		RegisterTimeout(IDLE_STATS_UPDATE_TIMEOUT,
 						IdleStatsUpdateTimeoutHandler);
+		RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT,
+						AnytimeStatsUpdateTimeoutHandler);
 	}
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index f16f35659b9..84e698da214 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -96,6 +96,7 @@ extern PGDLLIMPORT volatile sig_atomic_t IdleSessionTimeoutPending;
 extern PGDLLIMPORT volatile sig_atomic_t ProcSignalBarrierPending;
 extern PGDLLIMPORT volatile sig_atomic_t LogMemoryContextPending;
 extern PGDLLIMPORT volatile sig_atomic_t IdleStatsUpdateTimeoutPending;
+extern PGDLLIMPORT volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending;
 
 extern PGDLLIMPORT volatile sig_atomic_t CheckClientConnectionPending;
 extern PGDLLIMPORT volatile sig_atomic_t ClientConnectionLost;
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 9bb777c3d5a..b011a315679 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -34,6 +34,9 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/* Minimum interval non-forced stats flushes */
+#define PGSTAT_MIN_INTERVAL	1000
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -532,8 +535,24 @@ extern void pgstat_initialize(void);
 
 /* Functions called from backends */
 extern long pgstat_report_stat(bool force);
+extern void pgstat_report_anytime_stat(bool force);
 extern void pgstat_force_next_flush(void);
 
+/*
+ * Schedule the next anytime stats update timeout.
+ *
+ * This should be called whenever accumulating statistics that support
+ * FLUSH_ANYTIME flushing mode.
+ */
+#define pgstat_schedule_anytime_update()												\
+	do {																				\
+		if (IsUnderPostmaster && !pgstat_pending_anytime)								\
+		{																				\
+			enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);	\
+			pgstat_pending_anytime = true;												\
+		}																				\
+	} while (0)
+
 extern void pgstat_reset_counters(void);
 extern void pgstat_reset(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_reset_of_kind(PgStat_Kind kind);
@@ -806,6 +825,8 @@ extern PgStat_WalStats *pgstat_fetch_stat_wal(void);
  * Variables in pgstat.c
  */
 
+extern PGDLLIMPORT bool pgstat_pending_anytime;
+
 /* GUC parameters */
 extern PGDLLIMPORT bool pgstat_track_counts;
 extern PGDLLIMPORT int pgstat_track_functions;
@@ -849,4 +870,5 @@ extern PGDLLIMPORT PgStat_Counter pgStatTransactionIdleTime;
 /* updated by the traffic cop and in errfinish() */
 extern PGDLLIMPORT SessionEndType pgStatSessionEndCause;
 
+
 #endif							/* PGSTAT_H */
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..607f4255268 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -224,6 +224,19 @@ typedef struct PgStat_SubXactStatus
 	PgStat_TableXactStatus *first;	/* head of list for this subxact */
 } PgStat_SubXactStatus;
 
+/*
+ * Flush mode for statistics kinds.
+ *
+ * FLUSH_AT_TXN_BOUNDARY has to be the first because we want it to be the
+ * default value.
+ */
+typedef enum PgStat_FlushMode
+{
+	FLUSH_AT_TXN_BOUNDARY,		/* All fields can only be flushed at
+								 * transaction boundary */
+	FLUSH_ANYTIME,				/* All fields can be flushed anytime,
+								 * including within transactions */
+} PgStat_FlushMode;
 
 /*
  * Metadata for a specific kind of statistics.
@@ -251,6 +264,16 @@ typedef struct PgStat_KindInfo
 	 */
 	bool		track_entry_count:1;
 
+	/*
+	 * The mode of when to flush stats. See PgStat_FlushMode for more details.
+	 *
+	 * This member only has meaning for statistics kinds that accumulate
+	 * pending stats and use flush callbacks. For kinds that write directly to
+	 * shared memory (e.g., archiver, bgwriter, checkpointer), this member has
+	 * no effect.
+	 */
+	PgStat_FlushMode flush_mode;
+
 	/*
 	 * The size of an entry in the shared stats hash table (pointed to by
 	 * PgStatShared_HashEntry->body).  For fixed-numbered statistics, this is
@@ -297,8 +320,10 @@ typedef struct PgStat_KindInfo
 	 * For variable-numbered stats: flush pending stats. Required if pending
 	 * data is used. See flush_static_cb when dealing with stats data that
 	 * that cannot use PgStat_EntryRef->pending.
+	 *
+	 * The anytime_only parameter indicates whether this is an anytime flush.
 	 */
-	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait);
+	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait, bool anytime_only);
 
 	/*
 	 * For variable-numbered stats: delete pending stats. Optional.
@@ -366,8 +391,10 @@ typedef struct PgStat_KindInfo
 	 *
 	 * "pgstat_report_fixed" needs to be set to trigger the flush of pending
 	 * stats.
+	 *
+	 * The anytime_only parameter indicates whether this is an anytime flush.
 	 */
-	bool		(*flush_static_cb) (bool nowait);
+	bool		(*flush_static_cb) (bool nowait, bool anytime_only);
 
 	/*
 	 * For fixed-numbered statistics: Reset All.
@@ -677,6 +704,7 @@ extern PgStat_EntryRef *pgstat_fetch_pending_entry(PgStat_Kind kind,
 
 extern void *pgstat_fetch_entry(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_snapshot_fixed(PgStat_Kind kind);
+extern void AnytimeStatsUpdateTimeoutHandler(void);
 
 
 /*
@@ -696,8 +724,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL)
 
-extern bool pgstat_flush_backend(bool nowait, bits32 flags);
-extern bool pgstat_backend_flush_cb(bool nowait);
+extern bool pgstat_flush_backend(bool nowait, bits32 flags, bool anytime_only);
+extern bool pgstat_backend_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header,
 											  TimestampTz ts);
 
@@ -729,7 +757,7 @@ extern void AtEOXact_PgStat_Database(bool isCommit, bool parallel);
 
 extern PgStat_StatDBEntry *pgstat_prep_database_pending(Oid dboid);
 extern void pgstat_reset_database_timestamp(Oid dboid, TimestampTz ts);
-extern bool pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_database_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
@@ -737,7 +765,7 @@ extern void pgstat_database_reset_timestamp_cb(PgStatShared_Common *header, Time
  * Functions in pgstat_function.c
  */
 
-extern bool pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_function_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
@@ -745,9 +773,9 @@ extern void pgstat_function_reset_timestamp_cb(PgStatShared_Common *header, Time
  * Functions in pgstat_io.c
  */
 
-extern void pgstat_flush_io(bool nowait);
+extern void pgstat_flush_io(bool nowait, bool anytime_only);
 
-extern bool pgstat_io_flush_cb(bool nowait);
+extern bool pgstat_io_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_io_init_shmem_cb(void *stats);
 extern void pgstat_io_reset_all_cb(TimestampTz ts);
 extern void pgstat_io_snapshot_cb(void);
@@ -762,7 +790,7 @@ extern void AtEOSubXact_PgStat_Relations(PgStat_SubXactStatus *xact_state, bool
 extern void AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 
-extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
@@ -809,7 +837,7 @@ extern PgStatShared_Common *pgstat_init_entry(PgStat_Kind kind,
  * Functions in pgstat_slru.c
  */
 
-extern bool pgstat_slru_flush_cb(bool nowait);
+extern bool pgstat_slru_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_slru_init_shmem_cb(void *stats);
 extern void pgstat_slru_reset_all_cb(TimestampTz ts);
 extern void pgstat_slru_snapshot_cb(void);
@@ -820,7 +848,7 @@ extern void pgstat_slru_snapshot_cb(void);
  */
 
 extern void pgstat_wal_init_backend_cb(void);
-extern bool pgstat_wal_flush_cb(bool nowait);
+extern bool pgstat_wal_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_wal_init_shmem_cb(void *stats);
 extern void pgstat_wal_reset_all_cb(TimestampTz ts);
 extern void pgstat_wal_snapshot_cb(void);
@@ -830,7 +858,7 @@ extern void pgstat_wal_snapshot_cb(void);
  * Functions in pgstat_subscription.c
  */
 
-extern bool pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_subscription_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h
index 0965b590b34..10723bb664c 100644
--- a/src/include/utils/timeout.h
+++ b/src/include/utils/timeout.h
@@ -35,6 +35,7 @@ typedef enum TimeoutId
 	IDLE_SESSION_TIMEOUT,
 	IDLE_STATS_UPDATE_TIMEOUT,
 	CLIENT_CONNECTION_CHECK_TIMEOUT,
+	ANYTIME_STATS_UPDATE_TIMEOUT,
 	STARTUP_PROGRESS_TIMEOUT,
 	/* First user-definable timeout reason */
 	USER_TIMEOUT,
diff --git a/src/test/modules/test_custom_stats/test_custom_var_stats.c b/src/test/modules/test_custom_stats/test_custom_var_stats.c
index da28afbd929..4c207611236 100644
--- a/src/test/modules/test_custom_stats/test_custom_var_stats.c
+++ b/src/test/modules/test_custom_stats/test_custom_var_stats.c
@@ -84,7 +84,7 @@ static dsa_area *custom_stats_description_dsa = NULL;
 
 /* Flush callback: merge pending stats into shared memory */
 static bool test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref,
-												   bool nowait);
+												   bool nowait, bool anytime_only);
 
 /* Serialization callback: write auxiliary entry data */
 static void test_custom_stats_var_to_serialized_data(const PgStat_HashKey *key,
@@ -151,7 +151,7 @@ _PG_init(void)
  * Returns false only if nowait=true and lock acquisition fails.
  */
 static bool
-test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref, bool nowait)
+test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_StatCustomVarEntry *pending_entry;
 	PgStatShared_CustomVarEntry *shared_entry;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 241945734ec..1dbc4b96f51 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2271,6 +2271,7 @@ PgStat_Counter
 PgStat_EntryRef
 PgStat_EntryRefHashEntry
 PgStat_FetchConsistency
+PgStat_FlushMode
 PgStat_FunctionCallUsage
 PgStat_FunctionCounts
 PgStat_HashKey
-- 
2.34.1


--NVvBxFuyV/R+1/8/
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v10-0002-Add-anytime-flush-tests-for-custom-stats.patch"



^ permalink  raw  reply  [nested|flat] 12+ messages in thread

* [PATCH v3 1/3] Add pgstat_report_anytime_stat() for periodic stats flushing
@ 2026-01-05 09:41 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-05 09:41 UTC (permalink / raw)

Long running transactions can accumulate significant statistics (WAL, IO, ...)
that remain unflushed until the transaction ends. This delays visibility of
resource usage in monitoring views like pg_stat_io and pg_stat_wal.

This commit introduces pgstat_report_anytime_stat(), which flushes
non transactional statistics even inside active transactions. A new timeout
handler fires every second to call this function, ensuring timely stats visibility
without waiting for transaction completion.

Implementation details:

- Add PgStat_FlushMode enum to classify stats kinds:
  * FLUSH_ANYTIME: Stats that can always be flushed (WAL, IO, ...)
  * FLUSH_AT_TXN_BOUNDARY: Stats requiring transaction boundaries

- Modify pgstat_flush_pending_entries() and pgstat_flush_fixed_stats()
  to accept a boolean anytime_only parameter:
  * When false: flushes all stats (existing behavior)
  * When true: flushes only FLUSH_ANYTIME stats and skips FLUSH_AT_TXN_BOUNDARY stats

- This relies on the existing PGSTAT_MIN_INTERVAL to fire every 1 second, calling
pgstat_report_anytime_stat(false)

The force parameter in pgstat_report_anytime_stat() is currently unused (always
called with force=false) but reserved for future use cases requiring immediate
flushing.
---
 src/backend/tcop/postgres.c         |  16 ++++
 src/backend/utils/activity/pgstat.c | 111 +++++++++++++++++++++++-----
 src/backend/utils/init/globals.c    |   1 +
 src/backend/utils/init/postinit.c   |  15 ++++
 src/include/miscadmin.h             |   1 +
 src/include/pgstat.h                |   4 +
 src/include/utils/pgstat_internal.h |  16 ++++
 src/include/utils/timeout.h         |   1 +
 src/tools/pgindent/typedefs.list    |   1 +
 9 files changed, 148 insertions(+), 18 deletions(-)
   8.1% src/backend/tcop/
  68.4% src/backend/utils/activity/
   9.6% src/backend/utils/init/
   9.2% src/include/utils/
   4.1% src/include/

diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index e54bf1e760f..132fae61423 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -3530,6 +3530,22 @@ ProcessInterrupts(void)
 		pgstat_report_stat(true);
 	}
 
+	/*
+	 * Flush stats outside of transaction boundary if the timeout fired.
+	 * Unlike transactional stats, these can be flushed even inside a running
+	 * transaction.
+	 */
+	if (AnytimeStatsUpdateTimeoutPending)
+	{
+		AnytimeStatsUpdateTimeoutPending = false;
+
+		pgstat_report_anytime_stat(false);
+
+		/* Schedule next timeout */
+		enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT,
+							 PGSTAT_MIN_INTERVAL);
+	}
+
 	if (ProcSignalBarrierPending)
 		ProcessProcSignalBarrier();
 
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 11bb71cad5a..ab4d9088a9a 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -122,8 +122,6 @@
  * ----------
  */
 
-/* minimum interval non-forced stats flushes.*/
-#define PGSTAT_MIN_INTERVAL			1000
 /* how long until to block flushing pending stats updates */
 #define PGSTAT_MAX_INTERVAL			60000
 /* when to call pgstat_report_stat() again, even when idle */
@@ -187,7 +185,8 @@ static void pgstat_init_snapshot_fixed(void);
 
 static void pgstat_reset_after_failure(void);
 
-static bool pgstat_flush_pending_entries(bool nowait);
+static bool pgstat_flush_pending_entries(bool nowait, bool anytime_only);
+static bool pgstat_flush_fixed_stats(bool nowait, bool anytime_only);
 
 static void pgstat_prep_snapshot(void);
 static void pgstat_build_snapshot(void);
@@ -288,6 +287,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_database entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -305,6 +305,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Relation),
 		.shared_data_off = offsetof(PgStatShared_Relation, stats),
@@ -321,6 +322,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Function),
 		.shared_data_off = offsetof(PgStatShared_Function, stats),
@@ -336,6 +338,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.accessed_across_databases = true,
 
@@ -353,6 +356,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_subscription_stats entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -370,6 +374,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = false,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.accessed_across_databases = true,
 
@@ -388,6 +393,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, archiver),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, archiver),
@@ -404,6 +410,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, bgwriter),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, bgwriter),
@@ -420,6 +427,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, checkpointer),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, checkpointer),
@@ -436,6 +444,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
@@ -453,6 +462,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, slru),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, slru),
@@ -470,6 +480,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, wal),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, wal),
@@ -775,23 +786,11 @@ pgstat_report_stat(bool force)
 	partial_flush = false;
 
 	/* flush of variable-numbered stats tracked in pending entries list */
-	partial_flush |= pgstat_flush_pending_entries(nowait);
+	partial_flush |= pgstat_flush_pending_entries(nowait, false);
 
 	/* flush of other stats kinds */
 	if (pgstat_report_fixed)
-	{
-		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;
-
-			partial_flush |= kind_info->flush_static_cb(nowait);
-		}
-	}
+		partial_flush |= pgstat_flush_fixed_stats(nowait, false);
 
 	last_flush = now;
 
@@ -1345,9 +1344,14 @@ pgstat_delete_pending_entry(PgStat_EntryRef *entry_ref)
 
 /*
  * Flush out pending variable-numbered stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME entries.
+ * This is safe to call inside transactions.
+ *
+ * If anytime_only is false, flushes all entries.
  */
 static bool
-pgstat_flush_pending_entries(bool nowait)
+pgstat_flush_pending_entries(bool nowait, bool anytime_only)
 {
 	bool		have_pending = false;
 	dlist_node *cur = NULL;
@@ -1377,6 +1381,20 @@ pgstat_flush_pending_entries(bool nowait)
 		Assert(!kind_info->fixed_amount);
 		Assert(kind_info->flush_pending_cb != NULL);
 
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+		{
+			have_pending = true;
+
+			if (dlist_has_next(&pgStatPending, cur))
+				next = dlist_next_node(&pgStatPending, cur);
+			else
+				next = NULL;
+
+			cur = next;
+			continue;
+		}
+
 		/* flush the stats, if possible */
 		did_flush = kind_info->flush_pending_cb(entry_ref, nowait);
 
@@ -1402,6 +1420,33 @@ pgstat_flush_pending_entries(bool nowait)
 	return have_pending;
 }
 
+/*
+ * Flush fixed-amount stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME stats (safe inside transactions).
+ * If anytime_only is false, flushes all stats with flush_static_cb.
+ */
+static bool
+pgstat_flush_fixed_stats(bool nowait, bool anytime_only)
+{
+	bool		partial_flush = false;
+
+	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 || !kind_info->flush_static_cb)
+			continue;
+
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+			continue;
+
+		partial_flush |= kind_info->flush_static_cb(nowait);
+	}
+
+	return partial_flush;
+}
 
 /* ------------------------------------------------------------
  * Helper / infrastructure functions
@@ -2119,3 +2164,33 @@ assign_stats_fetch_consistency(int newval, void *extra)
 	if (pgstat_fetch_consistency != newval)
 		force_stats_snapshot_clear = true;
 }
+
+/*
+ * Flushes only FLUSH_ANYTIME stats using non-blocking locks. Transactional
+ * stats (FLUSH_AT_TXN_BOUNDARY) remain pending until transaction boundary.
+ * Safe to call inside transactions.
+ */
+void
+pgstat_report_anytime_stat(bool force)
+{
+	bool		nowait = !force;
+
+	pgstat_assert_is_up();
+
+	/*
+	 * Exit if no pending stats at all. This avoids unnecessary work when
+	 * backends are idle or in sessions without stats accumulation.
+	 *
+	 * Note: This check isn't precise as there might be only transactional
+	 * stats pending, which we'll skip during the flush. However, maintaining
+	 * precise tracking would add complexity that does not seem worth it from
+	 * a performance point of view (no noticeable performance regression has
+	 * been observed with the current implementation).
+	 */
+	if (dlist_is_empty(&pgStatPending) && !pgstat_report_fixed)
+		return;
+
+	/* Flush stats outside of transaction boundary */
+	pgstat_flush_pending_entries(nowait, true);
+	pgstat_flush_fixed_stats(nowait, true);
+}
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 36ad708b360..ad44826c39e 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -40,6 +40,7 @@ volatile sig_atomic_t IdleSessionTimeoutPending = false;
 volatile sig_atomic_t ProcSignalBarrierPending = false;
 volatile sig_atomic_t LogMemoryContextPending = false;
 volatile sig_atomic_t IdleStatsUpdateTimeoutPending = false;
+volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending = false;
 volatile uint32 InterruptHoldoffCount = 0;
 volatile uint32 QueryCancelHoldoffCount = 0;
 volatile uint32 CritSectionCount = 0;
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 3f401faf3de..6076f531c4a 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -82,6 +82,7 @@ static void TransactionTimeoutHandler(void);
 static void IdleSessionTimeoutHandler(void);
 static void IdleStatsUpdateTimeoutHandler(void);
 static void ClientCheckTimeoutHandler(void);
+static void AnytimeStatsUpdateTimeoutHandler(void);
 static bool ThereIsAtLeastOneRole(void);
 static void process_startup_options(Port *port, bool am_superuser);
 static void process_settings(Oid databaseid, Oid roleid);
@@ -765,6 +766,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 		RegisterTimeout(CLIENT_CONNECTION_CHECK_TIMEOUT, ClientCheckTimeoutHandler);
 		RegisterTimeout(IDLE_STATS_UPDATE_TIMEOUT,
 						IdleStatsUpdateTimeoutHandler);
+		RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT,
+						AnytimeStatsUpdateTimeoutHandler);
+		enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);
 	}
 
 	/*
@@ -1446,3 +1450,14 @@ ThereIsAtLeastOneRole(void)
 
 	return result;
 }
+
+/*
+ * Timeout handler for flushing non-transactional stats.
+ */
+static void
+AnytimeStatsUpdateTimeoutHandler(void)
+{
+	AnytimeStatsUpdateTimeoutPending = true;
+	InterruptPending = true;
+	SetLatch(MyLatch);
+}
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index db559b39c4d..8aeb9628871 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -96,6 +96,7 @@ extern PGDLLIMPORT volatile sig_atomic_t IdleSessionTimeoutPending;
 extern PGDLLIMPORT volatile sig_atomic_t ProcSignalBarrierPending;
 extern PGDLLIMPORT volatile sig_atomic_t LogMemoryContextPending;
 extern PGDLLIMPORT volatile sig_atomic_t IdleStatsUpdateTimeoutPending;
+extern PGDLLIMPORT volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending;
 
 extern PGDLLIMPORT volatile sig_atomic_t CheckClientConnectionPending;
 extern PGDLLIMPORT volatile sig_atomic_t ClientConnectionLost;
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index fff7ecc2533..1651f16f966 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -35,6 +35,9 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/* Minimum interval non-forced stats flushes */
+#define PGSTAT_MIN_INTERVAL	1000
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -533,6 +536,7 @@ extern void pgstat_initialize(void);
 
 /* Functions called from backends */
 extern long pgstat_report_stat(bool force);
+extern void pgstat_report_anytime_stat(bool force);
 extern void pgstat_force_next_flush(void);
 
 extern void pgstat_reset_counters(void);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..46ce90c9624 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -224,6 +224,19 @@ typedef struct PgStat_SubXactStatus
 	PgStat_TableXactStatus *first;	/* head of list for this subxact */
 } PgStat_SubXactStatus;
 
+/*
+ * Flush mode for statistics kinds.
+ *
+ * FLUSH_AT_TXN_BOUNDARY has to be the first because we want it to be the
+ * default value.
+ */
+typedef enum PgStat_FlushMode
+{
+	FLUSH_AT_TXN_BOUNDARY,		/* All fields can only be flushed at
+								 * transaction boundary */
+	FLUSH_ANYTIME,				/* All fields can be flushed anytime,
+								 * including within transactions */
+} PgStat_FlushMode;
 
 /*
  * Metadata for a specific kind of statistics.
@@ -251,6 +264,9 @@ typedef struct PgStat_KindInfo
 	 */
 	bool		track_entry_count:1;
 
+	/* Flush mode */
+	PgStat_FlushMode flush_mode;
+
 	/*
 	 * The size of an entry in the shared stats hash table (pointed to by
 	 * PgStatShared_HashEntry->body).  For fixed-numbered statistics, this is
diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h
index 0965b590b34..10723bb664c 100644
--- a/src/include/utils/timeout.h
+++ b/src/include/utils/timeout.h
@@ -35,6 +35,7 @@ typedef enum TimeoutId
 	IDLE_SESSION_TIMEOUT,
 	IDLE_STATS_UPDATE_TIMEOUT,
 	CLIENT_CONNECTION_CHECK_TIMEOUT,
+	ANYTIME_STATS_UPDATE_TIMEOUT,
 	STARTUP_PROGRESS_TIMEOUT,
 	/* First user-definable timeout reason */
 	USER_TIMEOUT,
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 3f3a888fd0e..d3912b43fdc 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2268,6 +2268,7 @@ PgStat_Counter
 PgStat_EntryRef
 PgStat_EntryRefHashEntry
 PgStat_FetchConsistency
+PgStat_FlushMode
 PgStat_FunctionCallUsage
 PgStat_FunctionCounts
 PgStat_HashKey
-- 
2.34.1


--lCc1MWfC7i2uqs8g
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0002-Remove-useless-calls-to-flush-some-stats.patch"



^ permalink  raw  reply  [nested|flat] 12+ messages in thread

* [PATCH v4 1/4] Add pgstat_report_anytime_stat() for periodic stats flushing
@ 2026-01-05 09:41 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-05 09:41 UTC (permalink / raw)

Long running transactions can accumulate significant statistics (WAL, IO, ...)
that remain unflushed until the transaction ends. This delays visibility of
resource usage in monitoring views like pg_stat_io and pg_stat_wal.

This commit introduces pgstat_report_anytime_stat(), which flushes
non transactional statistics even inside active transactions. A new timeout
handler fires every second to call this function, ensuring timely stats visibility
without waiting for transaction completion.

Implementation details:

- Add PgStat_FlushMode enum to classify stats kinds:
  * FLUSH_ANYTIME: Stats that can always be flushed (WAL, IO, ...)
  * FLUSH_AT_TXN_BOUNDARY: Stats requiring transaction boundaries

- Modify pgstat_flush_pending_entries() and pgstat_flush_fixed_stats()
  to accept a boolean anytime_only parameter:
  * When false: flushes all stats (existing behavior)
  * When true: flushes only FLUSH_ANYTIME stats and skips FLUSH_AT_TXN_BOUNDARY stats

- This relies on the existing PGSTAT_MIN_INTERVAL to fire every 1 second, calling
pgstat_report_anytime_stat(false)

The force parameter in pgstat_report_anytime_stat() is currently unused (always
called with force=false) but reserved for future use cases requiring immediate
flushing.
---
 src/backend/storage/lmgr/proc.c     |  10 +++
 src/backend/tcop/postgres.c         |  16 ++++
 src/backend/utils/activity/pgstat.c | 111 +++++++++++++++++++++++-----
 src/backend/utils/init/globals.c    |   1 +
 src/backend/utils/init/postinit.c   |  15 ++++
 src/include/miscadmin.h             |   1 +
 src/include/pgstat.h                |   4 +
 src/include/utils/pgstat_internal.h |  20 +++++
 src/include/utils/timeout.h         |   1 +
 src/tools/pgindent/typedefs.list    |   1 +
 10 files changed, 162 insertions(+), 18 deletions(-)
   7.0% src/backend/storage/lmgr/
   7.3% src/backend/tcop/
  61.1% src/backend/utils/activity/
   8.6% src/backend/utils/init/
  11.8% src/include/utils/
   3.6% src/include/

diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 063826ae576..012705a2ee6 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -1322,6 +1322,7 @@ ProcSleep(LOCALLOCK *locallock)
 	bool		allow_autovacuum_cancel = true;
 	bool		logged_recovery_conflict = false;
 	ProcWaitStatus myWaitStatus;
+	bool		anytime_timeout_was_active = false;
 
 	/* The caller must've armed the on-error cleanup mechanism */
 	Assert(GetAwaitedLock() == locallock);
@@ -1398,6 +1399,12 @@ ProcSleep(LOCALLOCK *locallock)
 		standbyWaitStart = GetCurrentTimestamp();
 	}
 
+	anytime_timeout_was_active = get_timeout_active(ANYTIME_STATS_UPDATE_TIMEOUT);
+
+	/* No need to try to flush the statistics while the process is sleeping */
+	if (anytime_timeout_was_active)
+		disable_timeout(ANYTIME_STATS_UPDATE_TIMEOUT, false);
+
 	/*
 	 * If somebody wakes us between LWLockRelease and WaitLatch, the latch
 	 * will not wait. But a set latch does not necessarily mean that the lock
@@ -1661,6 +1668,9 @@ ProcSleep(LOCALLOCK *locallock)
 		}
 	} while (myWaitStatus == PROC_WAIT_STATUS_WAITING);
 
+	if (anytime_timeout_was_active)
+		enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);
+
 	/*
 	 * Disable the timers, if they are still running.  As in LockErrorCleanup,
 	 * we must preserve the LOCK_TIMEOUT indicator flag: if a lock timeout has
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index e54bf1e760f..132fae61423 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -3530,6 +3530,22 @@ ProcessInterrupts(void)
 		pgstat_report_stat(true);
 	}
 
+	/*
+	 * Flush stats outside of transaction boundary if the timeout fired.
+	 * Unlike transactional stats, these can be flushed even inside a running
+	 * transaction.
+	 */
+	if (AnytimeStatsUpdateTimeoutPending)
+	{
+		AnytimeStatsUpdateTimeoutPending = false;
+
+		pgstat_report_anytime_stat(false);
+
+		/* Schedule next timeout */
+		enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT,
+							 PGSTAT_MIN_INTERVAL);
+	}
+
 	if (ProcSignalBarrierPending)
 		ProcessProcSignalBarrier();
 
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 11bb71cad5a..ab4d9088a9a 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -122,8 +122,6 @@
  * ----------
  */
 
-/* minimum interval non-forced stats flushes.*/
-#define PGSTAT_MIN_INTERVAL			1000
 /* how long until to block flushing pending stats updates */
 #define PGSTAT_MAX_INTERVAL			60000
 /* when to call pgstat_report_stat() again, even when idle */
@@ -187,7 +185,8 @@ static void pgstat_init_snapshot_fixed(void);
 
 static void pgstat_reset_after_failure(void);
 
-static bool pgstat_flush_pending_entries(bool nowait);
+static bool pgstat_flush_pending_entries(bool nowait, bool anytime_only);
+static bool pgstat_flush_fixed_stats(bool nowait, bool anytime_only);
 
 static void pgstat_prep_snapshot(void);
 static void pgstat_build_snapshot(void);
@@ -288,6 +287,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_database entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -305,6 +305,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Relation),
 		.shared_data_off = offsetof(PgStatShared_Relation, stats),
@@ -321,6 +322,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Function),
 		.shared_data_off = offsetof(PgStatShared_Function, stats),
@@ -336,6 +338,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.accessed_across_databases = true,
 
@@ -353,6 +356,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_subscription_stats entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -370,6 +374,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = false,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.accessed_across_databases = true,
 
@@ -388,6 +393,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, archiver),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, archiver),
@@ -404,6 +410,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, bgwriter),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, bgwriter),
@@ -420,6 +427,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, checkpointer),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, checkpointer),
@@ -436,6 +444,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
@@ -453,6 +462,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, slru),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, slru),
@@ -470,6 +480,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, wal),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, wal),
@@ -775,23 +786,11 @@ pgstat_report_stat(bool force)
 	partial_flush = false;
 
 	/* flush of variable-numbered stats tracked in pending entries list */
-	partial_flush |= pgstat_flush_pending_entries(nowait);
+	partial_flush |= pgstat_flush_pending_entries(nowait, false);
 
 	/* flush of other stats kinds */
 	if (pgstat_report_fixed)
-	{
-		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;
-
-			partial_flush |= kind_info->flush_static_cb(nowait);
-		}
-	}
+		partial_flush |= pgstat_flush_fixed_stats(nowait, false);
 
 	last_flush = now;
 
@@ -1345,9 +1344,14 @@ pgstat_delete_pending_entry(PgStat_EntryRef *entry_ref)
 
 /*
  * Flush out pending variable-numbered stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME entries.
+ * This is safe to call inside transactions.
+ *
+ * If anytime_only is false, flushes all entries.
  */
 static bool
-pgstat_flush_pending_entries(bool nowait)
+pgstat_flush_pending_entries(bool nowait, bool anytime_only)
 {
 	bool		have_pending = false;
 	dlist_node *cur = NULL;
@@ -1377,6 +1381,20 @@ pgstat_flush_pending_entries(bool nowait)
 		Assert(!kind_info->fixed_amount);
 		Assert(kind_info->flush_pending_cb != NULL);
 
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+		{
+			have_pending = true;
+
+			if (dlist_has_next(&pgStatPending, cur))
+				next = dlist_next_node(&pgStatPending, cur);
+			else
+				next = NULL;
+
+			cur = next;
+			continue;
+		}
+
 		/* flush the stats, if possible */
 		did_flush = kind_info->flush_pending_cb(entry_ref, nowait);
 
@@ -1402,6 +1420,33 @@ pgstat_flush_pending_entries(bool nowait)
 	return have_pending;
 }
 
+/*
+ * Flush fixed-amount stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME stats (safe inside transactions).
+ * If anytime_only is false, flushes all stats with flush_static_cb.
+ */
+static bool
+pgstat_flush_fixed_stats(bool nowait, bool anytime_only)
+{
+	bool		partial_flush = false;
+
+	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 || !kind_info->flush_static_cb)
+			continue;
+
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+			continue;
+
+		partial_flush |= kind_info->flush_static_cb(nowait);
+	}
+
+	return partial_flush;
+}
 
 /* ------------------------------------------------------------
  * Helper / infrastructure functions
@@ -2119,3 +2164,33 @@ assign_stats_fetch_consistency(int newval, void *extra)
 	if (pgstat_fetch_consistency != newval)
 		force_stats_snapshot_clear = true;
 }
+
+/*
+ * Flushes only FLUSH_ANYTIME stats using non-blocking locks. Transactional
+ * stats (FLUSH_AT_TXN_BOUNDARY) remain pending until transaction boundary.
+ * Safe to call inside transactions.
+ */
+void
+pgstat_report_anytime_stat(bool force)
+{
+	bool		nowait = !force;
+
+	pgstat_assert_is_up();
+
+	/*
+	 * Exit if no pending stats at all. This avoids unnecessary work when
+	 * backends are idle or in sessions without stats accumulation.
+	 *
+	 * Note: This check isn't precise as there might be only transactional
+	 * stats pending, which we'll skip during the flush. However, maintaining
+	 * precise tracking would add complexity that does not seem worth it from
+	 * a performance point of view (no noticeable performance regression has
+	 * been observed with the current implementation).
+	 */
+	if (dlist_is_empty(&pgStatPending) && !pgstat_report_fixed)
+		return;
+
+	/* Flush stats outside of transaction boundary */
+	pgstat_flush_pending_entries(nowait, true);
+	pgstat_flush_fixed_stats(nowait, true);
+}
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 36ad708b360..ad44826c39e 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -40,6 +40,7 @@ volatile sig_atomic_t IdleSessionTimeoutPending = false;
 volatile sig_atomic_t ProcSignalBarrierPending = false;
 volatile sig_atomic_t LogMemoryContextPending = false;
 volatile sig_atomic_t IdleStatsUpdateTimeoutPending = false;
+volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending = false;
 volatile uint32 InterruptHoldoffCount = 0;
 volatile uint32 QueryCancelHoldoffCount = 0;
 volatile uint32 CritSectionCount = 0;
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 3f401faf3de..6076f531c4a 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -82,6 +82,7 @@ static void TransactionTimeoutHandler(void);
 static void IdleSessionTimeoutHandler(void);
 static void IdleStatsUpdateTimeoutHandler(void);
 static void ClientCheckTimeoutHandler(void);
+static void AnytimeStatsUpdateTimeoutHandler(void);
 static bool ThereIsAtLeastOneRole(void);
 static void process_startup_options(Port *port, bool am_superuser);
 static void process_settings(Oid databaseid, Oid roleid);
@@ -765,6 +766,9 @@ InitPostgres(const char *in_dbname, Oid dboid,
 		RegisterTimeout(CLIENT_CONNECTION_CHECK_TIMEOUT, ClientCheckTimeoutHandler);
 		RegisterTimeout(IDLE_STATS_UPDATE_TIMEOUT,
 						IdleStatsUpdateTimeoutHandler);
+		RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT,
+						AnytimeStatsUpdateTimeoutHandler);
+		enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);
 	}
 
 	/*
@@ -1446,3 +1450,14 @@ ThereIsAtLeastOneRole(void)
 
 	return result;
 }
+
+/*
+ * Timeout handler for flushing non-transactional stats.
+ */
+static void
+AnytimeStatsUpdateTimeoutHandler(void)
+{
+	AnytimeStatsUpdateTimeoutPending = true;
+	InterruptPending = true;
+	SetLatch(MyLatch);
+}
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index db559b39c4d..8aeb9628871 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -96,6 +96,7 @@ extern PGDLLIMPORT volatile sig_atomic_t IdleSessionTimeoutPending;
 extern PGDLLIMPORT volatile sig_atomic_t ProcSignalBarrierPending;
 extern PGDLLIMPORT volatile sig_atomic_t LogMemoryContextPending;
 extern PGDLLIMPORT volatile sig_atomic_t IdleStatsUpdateTimeoutPending;
+extern PGDLLIMPORT volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending;
 
 extern PGDLLIMPORT volatile sig_atomic_t CheckClientConnectionPending;
 extern PGDLLIMPORT volatile sig_atomic_t ClientConnectionLost;
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index fff7ecc2533..1651f16f966 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -35,6 +35,9 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/* Minimum interval non-forced stats flushes */
+#define PGSTAT_MIN_INTERVAL	1000
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -533,6 +536,7 @@ extern void pgstat_initialize(void);
 
 /* Functions called from backends */
 extern long pgstat_report_stat(bool force);
+extern void pgstat_report_anytime_stat(bool force);
 extern void pgstat_force_next_flush(void);
 
 extern void pgstat_reset_counters(void);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..9ca39ea9a9a 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -224,6 +224,19 @@ typedef struct PgStat_SubXactStatus
 	PgStat_TableXactStatus *first;	/* head of list for this subxact */
 } PgStat_SubXactStatus;
 
+/*
+ * Flush mode for statistics kinds.
+ *
+ * FLUSH_AT_TXN_BOUNDARY has to be the first because we want it to be the
+ * default value.
+ */
+typedef enum PgStat_FlushMode
+{
+	FLUSH_AT_TXN_BOUNDARY,		/* All fields can only be flushed at
+								 * transaction boundary */
+	FLUSH_ANYTIME,				/* All fields can be flushed anytime,
+								 * including within transactions */
+} PgStat_FlushMode;
 
 /*
  * Metadata for a specific kind of statistics.
@@ -251,6 +264,13 @@ typedef struct PgStat_KindInfo
 	 */
 	bool		track_entry_count:1;
 
+	/*
+	 * Some stats have to be updated only at transaction boundaries (such as
+	 * tuples_inserted updated, deleted), so it's very important to set the
+	 * right flush mode (FLUSH_AT_TXN_BOUNDARY being the default).
+	 */
+	PgStat_FlushMode flush_mode;
+
 	/*
 	 * The size of an entry in the shared stats hash table (pointed to by
 	 * PgStatShared_HashEntry->body).  For fixed-numbered statistics, this is
diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h
index 0965b590b34..10723bb664c 100644
--- a/src/include/utils/timeout.h
+++ b/src/include/utils/timeout.h
@@ -35,6 +35,7 @@ typedef enum TimeoutId
 	IDLE_SESSION_TIMEOUT,
 	IDLE_STATS_UPDATE_TIMEOUT,
 	CLIENT_CONNECTION_CHECK_TIMEOUT,
+	ANYTIME_STATS_UPDATE_TIMEOUT,
 	STARTUP_PROGRESS_TIMEOUT,
 	/* First user-definable timeout reason */
 	USER_TIMEOUT,
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index ddbe4c64971..af21c87234a 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2268,6 +2268,7 @@ PgStat_Counter
 PgStat_EntryRef
 PgStat_EntryRefHashEntry
 PgStat_FetchConsistency
+PgStat_FlushMode
 PgStat_FunctionCallUsage
 PgStat_FunctionCounts
 PgStat_HashKey
-- 
2.34.1


--wR/mWGXukst4NraF
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Add-GUC-to-specify-non-transactional-statistics-f.patch"



^ permalink  raw  reply  [nested|flat] 12+ messages in thread

* [PATCH v5 1/4] Add pgstat_report_anytime_stat() for periodic stats flushing
@ 2026-01-05 09:41 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-05 09:41 UTC (permalink / raw)

Long running transactions can accumulate significant statistics (WAL, IO, ...)
that remain unflushed until the transaction ends. This delays visibility of
resource usage in monitoring views like pg_stat_io and pg_stat_wal.

This commit introduces pgstat_report_anytime_stat(), which flushes
non transactional statistics even inside active transactions. A new timeout
handler fires every second (if enabled while adding pending stats) to call this
function, ensuring timely stats visibility without waiting for transaction completion.

Implementation details:

- Add PgStat_FlushMode enum to classify stats kinds:
  * FLUSH_ANYTIME: Stats that can always be flushed (WAL, IO, ...)
  * FLUSH_AT_TXN_BOUNDARY: Stats requiring transaction boundaries

- Modify pgstat_flush_pending_entries() and pgstat_flush_fixed_stats()
  to accept a boolean anytime_only parameter:
  * When false: flushes all stats (existing behavior)
  * When true: flushes only FLUSH_ANYTIME stats and skips FLUSH_AT_TXN_BOUNDARY stats

- This relies on the existing PGSTAT_MIN_INTERVAL to fire every 1 second, calling
pgstat_report_anytime_stat(false)

The force parameter in pgstat_report_anytime_stat() is currently unused (always
called with force=false) but reserved for future use cases requiring immediate
flushing.
---
 src/backend/access/transam/xlog.c           |   9 ++
 src/backend/postmaster/bgwriter.c           |   9 +-
 src/backend/postmaster/checkpointer.c       |  10 +-
 src/backend/postmaster/startup.c            |   2 +
 src/backend/postmaster/walsummarizer.c      |   9 +-
 src/backend/postmaster/walwriter.c          |   9 +-
 src/backend/replication/walreceiver.c       |   9 +-
 src/backend/tcop/postgres.c                 |  12 ++
 src/backend/utils/activity/pgstat.c         | 118 ++++++++++++++++----
 src/backend/utils/activity/pgstat_backend.c |   9 ++
 src/backend/utils/activity/pgstat_io.c      |   5 +
 src/backend/utils/activity/pgstat_slru.c    |   5 +
 src/backend/utils/init/globals.c            |   1 +
 src/backend/utils/init/postinit.c           |   3 +
 src/include/miscadmin.h                     |   1 +
 src/include/pgstat.h                        |   4 +
 src/include/utils/pgstat_internal.h         |  21 ++++
 src/include/utils/timeout.h                 |   1 +
 src/tools/pgindent/typedefs.list            |   1 +
 19 files changed, 213 insertions(+), 25 deletions(-)
   5.5% src/backend/access/transam/
  15.3% src/backend/postmaster/
   3.4% src/backend/replication/
   3.8% src/backend/tcop/
  57.0% src/backend/utils/activity/
   9.2% src/include/utils/
   5.3% src/

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..9503aea5b4d 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -1085,6 +1085,10 @@ XLogInsertRecord(XLogRecData *rdata,
 		pgWalUsage.wal_fpi += num_fpi;
 		pgWalUsage.wal_fpi_bytes += fpi_bytes;
 
+		/* Schedule next anytime stats update timeout */
+		if (IsUnderPostmaster && !get_timeout_active(ANYTIME_STATS_UPDATE_TIMEOUT))
+			enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);
+
 		/* Required for the flush of pending stats WAL data */
 		pgstat_report_fixed = true;
 	}
@@ -2066,6 +2070,11 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic)
 					pgWalUsage.wal_buffers_full++;
 					TRACE_POSTGRESQL_WAL_BUFFER_WRITE_DIRTY_DONE();
 
+					/* Schedule next anytime stats update timeout */
+					if (IsUnderPostmaster && !get_timeout_active(ANYTIME_STATS_UPDATE_TIMEOUT))
+						enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT,
+											 PGSTAT_MIN_INTERVAL);
+
 					/*
 					 * Required for the flush of pending stats WAL data, per
 					 * update of pgWalUsage.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 80e3088fc7e..ab5d0645026 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -49,7 +49,9 @@
 #include "storage/smgr.h"
 #include "storage/standby.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 /*
@@ -104,7 +106,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN);
@@ -114,6 +116,11 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * We just started, assume there has been either a shutdown or
 	 * end-of-recovery snapshot.
diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c
index 6482c21b8f9..6e187315613 100644
--- a/src/backend/postmaster/checkpointer.c
+++ b/src/backend/postmaster/checkpointer.c
@@ -66,8 +66,9 @@
 #include "utils/acl.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
-
+#include "utils/timeout.h"
 
 /*----------
  * Shared memory area for communication between checkpointer and backends
@@ -216,7 +217,7 @@ CheckpointerMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, ReqShutdownXLOG);
 	pqsignal(SIGTERM, SIG_IGN); /* ignore SIGTERM */
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SignalHandlerForShutdownRequest);
@@ -226,6 +227,11 @@ CheckpointerMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * Initialize so that first time-driven event happens at the correct time.
 	 */
diff --git a/src/backend/postmaster/startup.c b/src/backend/postmaster/startup.c
index a1a4f65f9a9..498d147f0da 100644
--- a/src/backend/postmaster/startup.c
+++ b/src/backend/postmaster/startup.c
@@ -32,6 +32,7 @@
 #include "storage/standby.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timeout.h"
 
 
@@ -246,6 +247,7 @@ StartupProcessMain(const void *startup_data, size_t startup_data_len)
 	RegisterTimeout(STANDBY_DEADLOCK_TIMEOUT, StandbyDeadLockHandler);
 	RegisterTimeout(STANDBY_TIMEOUT, StandbyTimeoutHandler);
 	RegisterTimeout(STANDBY_LOCK_TIMEOUT, StandbyLockTimeoutHandler);
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
 
 	/*
 	 * Unblock signals (they were blocked when the postmaster forked us)
diff --git a/src/backend/postmaster/walsummarizer.c b/src/backend/postmaster/walsummarizer.c
index c3d56c866d3..cec5dfdb430 100644
--- a/src/backend/postmaster/walsummarizer.c
+++ b/src/backend/postmaster/walsummarizer.c
@@ -48,6 +48,8 @@
 #include "storage/shmem.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 #include "utils/wait_event.h"
 
 /*
@@ -250,7 +252,7 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SignalHandlerForShutdownRequest);
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN); /* not used */
@@ -272,6 +274,11 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * If an exception is encountered, processing resumes here.
 	 */
diff --git a/src/backend/postmaster/walwriter.c b/src/backend/postmaster/walwriter.c
index 38ec8a4c8c7..7416ca703c9 100644
--- a/src/backend/postmaster/walwriter.c
+++ b/src/backend/postmaster/walwriter.c
@@ -61,7 +61,9 @@
 #include "storage/smgr.h"
 #include "utils/hsearch.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
+#include "utils/timeout.h"
 
 
 /*
@@ -107,7 +109,7 @@ WalWriterMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SignalHandlerForShutdownRequest);
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN); /* not used */
@@ -117,6 +119,11 @@ WalWriterMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * Create a memory context that we will do all our work in.  We do this so
 	 * that we can reset the context during error recovery and thereby avoid
diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index 8b99160ed0e..24d7ef795cb 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -77,7 +77,9 @@
 #include "utils/builtins.h"
 #include "utils/guc.h"
 #include "utils/pg_lsn.h"
+#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 
@@ -253,7 +255,7 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);
 	pqsignal(SIGTERM, die);		/* request shutdown */
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN);
@@ -261,6 +263,11 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/* Load the libpq-specific functions */
 	load_file("libpqwalreceiver", false);
 	if (WalReceiverFunctions == NULL)
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index b4a8d2f3a1c..d19aa45400d 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -3530,6 +3530,18 @@ ProcessInterrupts(void)
 		pgstat_report_stat(true);
 	}
 
+	/*
+	 * Flush stats outside of transaction boundary if the timeout fired.
+	 * Unlike transactional stats, these can be flushed even inside a running
+	 * transaction.
+	 */
+	if (AnytimeStatsUpdateTimeoutPending)
+	{
+		AnytimeStatsUpdateTimeoutPending = false;
+
+		pgstat_report_anytime_stat(false);
+	}
+
 	if (ProcSignalBarrierPending)
 		ProcessProcSignalBarrier();
 
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 11bb71cad5a..2c9454677e9 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -112,6 +112,7 @@
 #include "utils/guc_hooks.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 
@@ -122,8 +123,6 @@
  * ----------
  */
 
-/* minimum interval non-forced stats flushes.*/
-#define PGSTAT_MIN_INTERVAL			1000
 /* how long until to block flushing pending stats updates */
 #define PGSTAT_MAX_INTERVAL			60000
 /* when to call pgstat_report_stat() again, even when idle */
@@ -187,7 +186,8 @@ static void pgstat_init_snapshot_fixed(void);
 
 static void pgstat_reset_after_failure(void);
 
-static bool pgstat_flush_pending_entries(bool nowait);
+static bool pgstat_flush_pending_entries(bool nowait, bool anytime_only);
+static bool pgstat_flush_fixed_stats(bool nowait, bool anytime_only);
 
 static void pgstat_prep_snapshot(void);
 static void pgstat_build_snapshot(void);
@@ -288,6 +288,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_database entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -305,6 +306,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Relation),
 		.shared_data_off = offsetof(PgStatShared_Relation, stats),
@@ -321,6 +323,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Function),
 		.shared_data_off = offsetof(PgStatShared_Function, stats),
@@ -336,6 +339,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.accessed_across_databases = true,
 
@@ -353,6 +357,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_subscription_stats entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -370,6 +375,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = false,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.accessed_across_databases = true,
 
@@ -388,6 +394,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, archiver),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, archiver),
@@ -404,6 +411,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, bgwriter),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, bgwriter),
@@ -420,6 +428,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, checkpointer),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, checkpointer),
@@ -436,6 +445,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
@@ -453,6 +463,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, slru),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, slru),
@@ -470,6 +481,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, wal),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, wal),
@@ -775,23 +787,11 @@ pgstat_report_stat(bool force)
 	partial_flush = false;
 
 	/* flush of variable-numbered stats tracked in pending entries list */
-	partial_flush |= pgstat_flush_pending_entries(nowait);
+	partial_flush |= pgstat_flush_pending_entries(nowait, false);
 
 	/* flush of other stats kinds */
 	if (pgstat_report_fixed)
-	{
-		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;
-
-			partial_flush |= kind_info->flush_static_cb(nowait);
-		}
-	}
+		partial_flush |= pgstat_flush_fixed_stats(nowait, false);
 
 	last_flush = now;
 
@@ -1293,12 +1293,18 @@ pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid, uint64 objid, bool *creat
 
 	if (entry_ref->pending == NULL)
 	{
-		size_t		entrysize = pgstat_get_kind_info(kind)->pending_size;
+		const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
+		size_t		entrysize = kind_info->pending_size;
 
 		Assert(entrysize != (size_t) -1);
 
 		entry_ref->pending = MemoryContextAllocZero(pgStatPendingContext, entrysize);
 		dlist_push_tail(&pgStatPending, &entry_ref->pending_node);
+
+		/* Schedule next anytime stats update timeout */
+		if (kind_info->flush_mode == FLUSH_ANYTIME && IsUnderPostmaster &&
+			!get_timeout_active(ANYTIME_STATS_UPDATE_TIMEOUT))
+			enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);
 	}
 
 	return entry_ref;
@@ -1345,9 +1351,14 @@ pgstat_delete_pending_entry(PgStat_EntryRef *entry_ref)
 
 /*
  * Flush out pending variable-numbered stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME entries.
+ * This is safe to call inside transactions.
+ *
+ * If anytime_only is false, flushes all entries.
  */
 static bool
-pgstat_flush_pending_entries(bool nowait)
+pgstat_flush_pending_entries(bool nowait, bool anytime_only)
 {
 	bool		have_pending = false;
 	dlist_node *cur = NULL;
@@ -1377,6 +1388,20 @@ pgstat_flush_pending_entries(bool nowait)
 		Assert(!kind_info->fixed_amount);
 		Assert(kind_info->flush_pending_cb != NULL);
 
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+		{
+			have_pending = true;
+
+			if (dlist_has_next(&pgStatPending, cur))
+				next = dlist_next_node(&pgStatPending, cur);
+			else
+				next = NULL;
+
+			cur = next;
+			continue;
+		}
+
 		/* flush the stats, if possible */
 		did_flush = kind_info->flush_pending_cb(entry_ref, nowait);
 
@@ -1402,6 +1427,33 @@ pgstat_flush_pending_entries(bool nowait)
 	return have_pending;
 }
 
+/*
+ * Flush fixed-amount stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME stats (safe inside transactions).
+ * If anytime_only is false, flushes all stats with flush_static_cb.
+ */
+static bool
+pgstat_flush_fixed_stats(bool nowait, bool anytime_only)
+{
+	bool		partial_flush = false;
+
+	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 || !kind_info->flush_static_cb)
+			continue;
+
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+			continue;
+
+		partial_flush |= kind_info->flush_static_cb(nowait);
+	}
+
+	return partial_flush;
+}
 
 /* ------------------------------------------------------------
  * Helper / infrastructure functions
@@ -2119,3 +2171,31 @@ assign_stats_fetch_consistency(int newval, void *extra)
 	if (pgstat_fetch_consistency != newval)
 		force_stats_snapshot_clear = true;
 }
+
+/*
+ * Flushes only FLUSH_ANYTIME stats using non-blocking locks. Transactional
+ * stats (FLUSH_AT_TXN_BOUNDARY) remain pending until transaction boundary.
+ * Safe to call inside transactions.
+ */
+void
+pgstat_report_anytime_stat(bool force)
+{
+	bool		nowait = !force;
+
+	pgstat_assert_is_up();
+
+	/* Flush stats outside of transaction boundary */
+	pgstat_flush_pending_entries(nowait, true);
+	pgstat_flush_fixed_stats(nowait, true);
+}
+
+/*
+ * Timeout handler for flushing non-transactional stats.
+ */
+void
+AnytimeStatsUpdateTimeoutHandler(void)
+{
+	AnytimeStatsUpdateTimeoutPending = true;
+	InterruptPending = true;
+	SetLatch(MyLatch);
+}
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index 1350f5f62f1..9dcb24db975 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -31,6 +31,7 @@
 #include "storage/procarray.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 
 /*
  * Backend statistics counts waiting to be flushed out. These counters may be
@@ -66,6 +67,10 @@ pgstat_count_backend_io_op_time(IOObject io_object, IOContext io_context,
 	INSTR_TIME_ADD(PendingBackendStats.pending_io.pending_times[io_object][io_context][io_op],
 				   io_time);
 
+	/* Schedule next anytime stats update timeout */
+	if (IsUnderPostmaster && !get_timeout_active(ANYTIME_STATS_UPDATE_TIMEOUT))
+		enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);
+
 	backend_has_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -82,6 +87,10 @@ pgstat_count_backend_io_op(IOObject io_object, IOContext io_context,
 	PendingBackendStats.pending_io.counts[io_object][io_context][io_op] += cnt;
 	PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
 
+	/* Schedule next anytime stats update timeout */
+	if (IsUnderPostmaster && !get_timeout_active(ANYTIME_STATS_UPDATE_TIMEOUT))
+		enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);
+
 	backend_has_iostats = true;
 	pgstat_report_fixed = true;
 }
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 28de24538dc..53dbf2a514b 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -19,6 +19,7 @@
 #include "executor/instrument.h"
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
@@ -79,6 +80,10 @@ pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op,
 	/* Add the per-backend counts */
 	pgstat_count_backend_io_op(io_object, io_context, io_op, cnt, bytes);
 
+	/* Schedule next anytime stats update timeout */
+	if (IsUnderPostmaster && !get_timeout_active(ANYTIME_STATS_UPDATE_TIMEOUT))
+		enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);
+
 	have_iostats = true;
 	pgstat_report_fixed = true;
 }
diff --git a/src/backend/utils/activity/pgstat_slru.c b/src/backend/utils/activity/pgstat_slru.c
index 2190f388eae..1d16cde1889 100644
--- a/src/backend/utils/activity/pgstat_slru.c
+++ b/src/backend/utils/activity/pgstat_slru.c
@@ -19,6 +19,7 @@
 
 #include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
+#include "utils/timeout.h"
 
 
 static inline PgStat_SLRUStats *get_slru_entry(int slru_idx);
@@ -223,6 +224,10 @@ get_slru_entry(int slru_idx)
 
 	Assert((slru_idx >= 0) && (slru_idx < SLRU_NUM_ELEMENTS));
 
+	/* Schedule next anytime stats update timeout */
+	if (IsUnderPostmaster && !get_timeout_active(ANYTIME_STATS_UPDATE_TIMEOUT))
+		enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);
+
 	have_slrustats = true;
 	pgstat_report_fixed = true;
 
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 36ad708b360..ad44826c39e 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -40,6 +40,7 @@ volatile sig_atomic_t IdleSessionTimeoutPending = false;
 volatile sig_atomic_t ProcSignalBarrierPending = false;
 volatile sig_atomic_t LogMemoryContextPending = false;
 volatile sig_atomic_t IdleStatsUpdateTimeoutPending = false;
+volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending = false;
 volatile uint32 InterruptHoldoffCount = 0;
 volatile uint32 QueryCancelHoldoffCount = 0;
 volatile uint32 CritSectionCount = 0;
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 3f401faf3de..f45365f47f7 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -64,6 +64,7 @@
 #include "utils/injection_point.h"
 #include "utils/memutils.h"
 #include "utils/pg_locale.h"
+#include "utils/pgstat_internal.h"
 #include "utils/portal.h"
 #include "utils/ps_status.h"
 #include "utils/snapmgr.h"
@@ -765,6 +766,8 @@ InitPostgres(const char *in_dbname, Oid dboid,
 		RegisterTimeout(CLIENT_CONNECTION_CHECK_TIMEOUT, ClientCheckTimeoutHandler);
 		RegisterTimeout(IDLE_STATS_UPDATE_TIMEOUT,
 						IdleStatsUpdateTimeoutHandler);
+		RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT,
+						AnytimeStatsUpdateTimeoutHandler);
 	}
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index db559b39c4d..8aeb9628871 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -96,6 +96,7 @@ extern PGDLLIMPORT volatile sig_atomic_t IdleSessionTimeoutPending;
 extern PGDLLIMPORT volatile sig_atomic_t ProcSignalBarrierPending;
 extern PGDLLIMPORT volatile sig_atomic_t LogMemoryContextPending;
 extern PGDLLIMPORT volatile sig_atomic_t IdleStatsUpdateTimeoutPending;
+extern PGDLLIMPORT volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending;
 
 extern PGDLLIMPORT volatile sig_atomic_t CheckClientConnectionPending;
 extern PGDLLIMPORT volatile sig_atomic_t ClientConnectionLost;
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index fff7ecc2533..1651f16f966 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -35,6 +35,9 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/* Minimum interval non-forced stats flushes */
+#define PGSTAT_MIN_INTERVAL	1000
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -533,6 +536,7 @@ extern void pgstat_initialize(void);
 
 /* Functions called from backends */
 extern long pgstat_report_stat(bool force);
+extern void pgstat_report_anytime_stat(bool force);
 extern void pgstat_force_next_flush(void);
 
 extern void pgstat_reset_counters(void);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..a9190078d0e 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -224,6 +224,19 @@ typedef struct PgStat_SubXactStatus
 	PgStat_TableXactStatus *first;	/* head of list for this subxact */
 } PgStat_SubXactStatus;
 
+/*
+ * Flush mode for statistics kinds.
+ *
+ * FLUSH_AT_TXN_BOUNDARY has to be the first because we want it to be the
+ * default value.
+ */
+typedef enum PgStat_FlushMode
+{
+	FLUSH_AT_TXN_BOUNDARY,		/* All fields can only be flushed at
+								 * transaction boundary */
+	FLUSH_ANYTIME,				/* All fields can be flushed anytime,
+								 * including within transactions */
+} PgStat_FlushMode;
 
 /*
  * Metadata for a specific kind of statistics.
@@ -251,6 +264,13 @@ typedef struct PgStat_KindInfo
 	 */
 	bool		track_entry_count:1;
 
+	/*
+	 * Some stats have to be updated only at transaction boundaries (such as
+	 * tuples_inserted updated, deleted), so it's very important to set the
+	 * right flush mode (FLUSH_AT_TXN_BOUNDARY being the default).
+	 */
+	PgStat_FlushMode flush_mode;
+
 	/*
 	 * The size of an entry in the shared stats hash table (pointed to by
 	 * PgStatShared_HashEntry->body).  For fixed-numbered statistics, this is
@@ -677,6 +697,7 @@ extern PgStat_EntryRef *pgstat_fetch_pending_entry(PgStat_Kind kind,
 
 extern void *pgstat_fetch_entry(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_snapshot_fixed(PgStat_Kind kind);
+extern void AnytimeStatsUpdateTimeoutHandler(void);
 
 
 /*
diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h
index 0965b590b34..10723bb664c 100644
--- a/src/include/utils/timeout.h
+++ b/src/include/utils/timeout.h
@@ -35,6 +35,7 @@ typedef enum TimeoutId
 	IDLE_SESSION_TIMEOUT,
 	IDLE_STATS_UPDATE_TIMEOUT,
 	CLIENT_CONNECTION_CHECK_TIMEOUT,
+	ANYTIME_STATS_UPDATE_TIMEOUT,
 	STARTUP_PROGRESS_TIMEOUT,
 	/* First user-definable timeout reason */
 	USER_TIMEOUT,
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 9f5ee8fd482..860f835c088 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2268,6 +2268,7 @@ PgStat_Counter
 PgStat_EntryRef
 PgStat_EntryRefHashEntry
 PgStat_FetchConsistency
+PgStat_FlushMode
 PgStat_FunctionCallUsage
 PgStat_FunctionCounts
 PgStat_HashKey
-- 
2.34.1


--WLtTrIUEfQDmERxy
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0002-Add-GUC-to-specify-non-transactional-statistics-f.patch"



^ permalink  raw  reply  [nested|flat] 12+ messages in thread

* [PATCH v6 1/5] Add pgstat_report_anytime_stat() for periodic stats flushing
@ 2026-01-05 09:41 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-05 09:41 UTC (permalink / raw)

Long running transactions can accumulate significant statistics (WAL, IO, ...)
that remain unflushed until the transaction ends. This delays visibility of
resource usage in monitoring views like pg_stat_io and pg_stat_wal and produces
spikes when flushed.

This commit introduces pgstat_report_anytime_stat(), which flushes
non transactional statistics even inside active transactions. A new timeout
handler fires every second (if enabled while adding pending stats) to call this
function, ensuring timely stats visibility without waiting for transaction completion.

Implementation details:

- Add PgStat_FlushMode enum to classify stats kinds:
  * FLUSH_ANYTIME: Stats that can always be flushed (WAL, IO, ...)
  * FLUSH_AT_TXN_BOUNDARY: Stats requiring transaction boundaries

- Modify pgstat_flush_pending_entries() and pgstat_flush_fixed_stats()
  to accept a boolean anytime_only parameter:
  * When false: flushes all stats (existing behavior)
  * When true: flushes only FLUSH_ANYTIME stats and skips FLUSH_AT_TXN_BOUNDARY stats

- The flush_pending_cb and flush_static_cb callbacks now receive an anytime_only
boolean parameter. Most of the time it's not used (except for assertions), but it's
preparatory work for moving the relations stats to anytime (without introducin
a new callback).

- Add pgstat_schedule_anytime_update() macro to schedule the next anytime flush,
relying on PGSTAT_MIN_INTERVAL

The force parameter in pgstat_report_anytime_stat() is currently unused (always
called with force=false) but reserved for future use cases requiring immediate
flushing.
---
 src/backend/access/transam/xlog.c             |   6 +
 src/backend/postmaster/bgwriter.c             |   9 +-
 src/backend/postmaster/checkpointer.c         |  10 +-
 src/backend/postmaster/startup.c              |   2 +
 src/backend/postmaster/walsummarizer.c        |   9 +-
 src/backend/postmaster/walwriter.c            |   9 +-
 src/backend/replication/walreceiver.c         |   9 +-
 src/backend/replication/walsender.c           |   8 +-
 src/backend/tcop/postgres.c                   |  12 ++
 src/backend/utils/activity/pgstat.c           | 112 ++++++++++++++----
 src/backend/utils/activity/pgstat_backend.c   |  13 +-
 src/backend/utils/activity/pgstat_bgwriter.c  |   2 +-
 .../utils/activity/pgstat_checkpointer.c      |   2 +-
 src/backend/utils/activity/pgstat_database.c  |   2 +-
 src/backend/utils/activity/pgstat_function.c  |   4 +-
 src/backend/utils/activity/pgstat_io.c        |  10 +-
 src/backend/utils/activity/pgstat_relation.c  |  12 +-
 src/backend/utils/activity/pgstat_slru.c      |   6 +-
 .../utils/activity/pgstat_subscription.c      |   4 +-
 src/backend/utils/activity/pgstat_wal.c       |  10 +-
 src/backend/utils/init/globals.c              |   1 +
 src/backend/utils/init/postinit.c             |   3 +
 src/include/miscadmin.h                       |   1 +
 src/include/pgstat.h                          |  16 +++
 src/include/utils/pgstat_internal.h           |  52 ++++++--
 src/include/utils/timeout.h                   |   1 +
 .../test_custom_stats/test_custom_var_stats.c |   4 +-
 src/tools/pgindent/typedefs.list              |   1 +
 28 files changed, 264 insertions(+), 66 deletions(-)
  10.8% src/backend/postmaster/
   6.0% src/backend/replication/
  50.7% src/backend/utils/activity/
   6.0% src/backend/
  19.3% src/include/utils/
   5.6% src/include/

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 13ec6225b85..d01b11c7470 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -1085,6 +1085,9 @@ XLogInsertRecord(XLogRecData *rdata,
 		pgWalUsage.wal_fpi += num_fpi;
 		pgWalUsage.wal_fpi_bytes += fpi_bytes;
 
+		/* Schedule next anytime stats update timeout */
+		pgstat_schedule_anytime_update();
+
 		/* Required for the flush of pending stats WAL data */
 		pgstat_report_fixed = true;
 	}
@@ -2066,6 +2069,9 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic)
 					pgWalUsage.wal_buffers_full++;
 					TRACE_POSTGRESQL_WAL_BUFFER_WRITE_DIRTY_DONE();
 
+					/* Schedule next anytime stats update timeout */
+					pgstat_schedule_anytime_update();
+
 					/*
 					 * Required for the flush of pending stats WAL data, per
 					 * update of pgWalUsage.
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 0956bd39a85..059c601c3b8 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -49,7 +49,9 @@
 #include "storage/smgr.h"
 #include "storage/standby.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 /*
@@ -103,7 +105,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN);
@@ -113,6 +115,11 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * We just started, assume there has been either a shutdown or
 	 * end-of-recovery snapshot.
diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c
index e03c19123bc..e11c4b099c8 100644
--- a/src/backend/postmaster/checkpointer.c
+++ b/src/backend/postmaster/checkpointer.c
@@ -66,8 +66,9 @@
 #include "utils/acl.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
-
+#include "utils/timeout.h"
 
 /*----------
  * Shared memory area for communication between checkpointer and backends
@@ -215,7 +216,7 @@ CheckpointerMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, ReqShutdownXLOG);
 	pqsignal(SIGTERM, SIG_IGN); /* ignore SIGTERM */
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SignalHandlerForShutdownRequest);
@@ -225,6 +226,11 @@ CheckpointerMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * Initialize so that first time-driven event happens at the correct time.
 	 */
diff --git a/src/backend/postmaster/startup.c b/src/backend/postmaster/startup.c
index cdbe53dd262..4954fe425b7 100644
--- a/src/backend/postmaster/startup.c
+++ b/src/backend/postmaster/startup.c
@@ -32,6 +32,7 @@
 #include "storage/standby.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timeout.h"
 
 
@@ -245,6 +246,7 @@ StartupProcessMain(const void *startup_data, size_t startup_data_len)
 	RegisterTimeout(STANDBY_DEADLOCK_TIMEOUT, StandbyDeadLockHandler);
 	RegisterTimeout(STANDBY_TIMEOUT, StandbyTimeoutHandler);
 	RegisterTimeout(STANDBY_LOCK_TIMEOUT, StandbyLockTimeoutHandler);
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
 
 	/*
 	 * Unblock signals (they were blocked when the postmaster forked us)
diff --git a/src/backend/postmaster/walsummarizer.c b/src/backend/postmaster/walsummarizer.c
index 2d8f57099fd..9f8ef8159d1 100644
--- a/src/backend/postmaster/walsummarizer.c
+++ b/src/backend/postmaster/walsummarizer.c
@@ -48,6 +48,8 @@
 #include "storage/shmem.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 #include "utils/wait_event.h"
 
 /*
@@ -249,7 +251,7 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SignalHandlerForShutdownRequest);
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN); /* not used */
@@ -271,6 +273,11 @@ WalSummarizerMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * If an exception is encountered, processing resumes here.
 	 */
diff --git a/src/backend/postmaster/walwriter.c b/src/backend/postmaster/walwriter.c
index 23e79a32345..ded0f250288 100644
--- a/src/backend/postmaster/walwriter.c
+++ b/src/backend/postmaster/walwriter.c
@@ -61,7 +61,9 @@
 #include "storage/smgr.h"
 #include "utils/hsearch.h"
 #include "utils/memutils.h"
+#include "utils/pgstat_internal.h"
 #include "utils/resowner.h"
+#include "utils/timeout.h"
 
 
 /*
@@ -106,7 +108,7 @@ WalWriterMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SignalHandlerForShutdownRequest);
 	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN); /* not used */
@@ -116,6 +118,11 @@ WalWriterMain(const void *startup_data, size_t startup_data_len)
 	 */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/*
 	 * Create a memory context that we will do all our work in.  We do this so
 	 * that we can reset the context during error recovery and thereby avoid
diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index 10e64a7d1f4..11b7c114d3b 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -77,7 +77,9 @@
 #include "utils/builtins.h"
 #include "utils/guc.h"
 #include "utils/pg_lsn.h"
+#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 
@@ -252,7 +254,7 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 	pqsignal(SIGINT, SIG_IGN);
 	pqsignal(SIGTERM, die);		/* request shutdown */
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
-	pqsignal(SIGALRM, SIG_IGN);
+	InitializeTimeouts();		/* establishes SIGALRM handler */
 	pqsignal(SIGPIPE, SIG_IGN);
 	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, SIG_IGN);
@@ -260,6 +262,11 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
 
+	/*
+	 * Register timeouts needed
+	 */
+	RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT, AnytimeStatsUpdateTimeoutHandler);
+
 	/* Load the libpq-specific functions */
 	load_file("libpqwalreceiver", false);
 	if (WalReceiverFunctions == NULL)
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 2cde8ebc729..a7214d0dc6f 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -1987,8 +1987,8 @@ WalSndWaitForWal(XLogRecPtr loc)
 		if (TimestampDifferenceExceeds(last_flush, now,
 									   WALSENDER_STATS_FLUSH_INTERVAL))
 		{
-			pgstat_flush_io(false);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+			pgstat_flush_io(false, true);
+			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 			last_flush = now;
 		}
 
@@ -3016,8 +3016,8 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			if (TimestampDifferenceExceeds(last_flush, now,
 										   WALSENDER_STATS_FLUSH_INTERVAL))
 			{
-				pgstat_flush_io(false);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+				pgstat_flush_io(false, true);
+				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 				last_flush = now;
 			}
 
diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c
index 02e9aaa6bca..c7bc409b06f 100644
--- a/src/backend/tcop/postgres.c
+++ b/src/backend/tcop/postgres.c
@@ -3509,6 +3509,18 @@ ProcessInterrupts(void)
 		pgstat_report_stat(true);
 	}
 
+	/*
+	 * Flush stats outside of transaction boundary if the timeout fired.
+	 * Unlike transactional stats, these can be flushed even inside a running
+	 * transaction.
+	 */
+	if (AnytimeStatsUpdateTimeoutPending)
+	{
+		AnytimeStatsUpdateTimeoutPending = false;
+
+		pgstat_report_anytime_stat(false);
+	}
+
 	if (ProcSignalBarrierPending)
 		ProcessProcSignalBarrier();
 
diff --git a/src/backend/utils/activity/pgstat.c b/src/backend/utils/activity/pgstat.c
index 11bb71cad5a..411b65aae3e 100644
--- a/src/backend/utils/activity/pgstat.c
+++ b/src/backend/utils/activity/pgstat.c
@@ -112,6 +112,7 @@
 #include "utils/guc_hooks.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 #include "utils/timestamp.h"
 
 
@@ -122,8 +123,6 @@
  * ----------
  */
 
-/* minimum interval non-forced stats flushes.*/
-#define PGSTAT_MIN_INTERVAL			1000
 /* how long until to block flushing pending stats updates */
 #define PGSTAT_MAX_INTERVAL			60000
 /* when to call pgstat_report_stat() again, even when idle */
@@ -187,7 +186,8 @@ static void pgstat_init_snapshot_fixed(void);
 
 static void pgstat_reset_after_failure(void);
 
-static bool pgstat_flush_pending_entries(bool nowait);
+static bool pgstat_flush_pending_entries(bool nowait, bool anytime_only);
+static bool pgstat_flush_fixed_stats(bool nowait, bool anytime_only);
 
 static void pgstat_prep_snapshot(void);
 static void pgstat_build_snapshot(void);
@@ -288,6 +288,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_database entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -305,6 +306,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Relation),
 		.shared_data_off = offsetof(PgStatShared_Relation, stats),
@@ -321,6 +323,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.shared_size = sizeof(PgStatShared_Function),
 		.shared_data_off = offsetof(PgStatShared_Function, stats),
@@ -336,6 +339,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 
 		.accessed_across_databases = true,
 
@@ -353,6 +357,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = true,
+		.flush_mode = FLUSH_AT_TXN_BOUNDARY,
 		/* so pg_stat_subscription_stats entries can be seen in all databases */
 		.accessed_across_databases = true,
 
@@ -370,6 +375,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = false,
 		.write_to_file = false,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.accessed_across_databases = true,
 
@@ -436,6 +442,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, io),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, io),
@@ -453,6 +460,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, slru),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, slru),
@@ -470,6 +478,7 @@ static const PgStat_KindInfo pgstat_kind_builtin_infos[PGSTAT_KIND_BUILTIN_SIZE]
 
 		.fixed_amount = true,
 		.write_to_file = true,
+		.flush_mode = FLUSH_ANYTIME,
 
 		.snapshot_ctl_off = offsetof(PgStat_Snapshot, wal),
 		.shared_ctl_off = offsetof(PgStat_ShmemControl, wal),
@@ -775,23 +784,11 @@ pgstat_report_stat(bool force)
 	partial_flush = false;
 
 	/* flush of variable-numbered stats tracked in pending entries list */
-	partial_flush |= pgstat_flush_pending_entries(nowait);
+	partial_flush |= pgstat_flush_pending_entries(nowait, false);
 
 	/* flush of other stats kinds */
 	if (pgstat_report_fixed)
-	{
-		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;
-
-			partial_flush |= kind_info->flush_static_cb(nowait);
-		}
-	}
+		partial_flush |= pgstat_flush_fixed_stats(nowait, false);
 
 	last_flush = now;
 
@@ -1293,7 +1290,8 @@ pgstat_prep_pending_entry(PgStat_Kind kind, Oid dboid, uint64 objid, bool *creat
 
 	if (entry_ref->pending == NULL)
 	{
-		size_t		entrysize = pgstat_get_kind_info(kind)->pending_size;
+		const PgStat_KindInfo *kind_info = pgstat_get_kind_info(kind);
+		size_t		entrysize = kind_info->pending_size;
 
 		Assert(entrysize != (size_t) -1);
 
@@ -1345,9 +1343,14 @@ pgstat_delete_pending_entry(PgStat_EntryRef *entry_ref)
 
 /*
  * Flush out pending variable-numbered stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME entries.
+ * This is safe to call inside transactions.
+ *
+ * If anytime_only is false, flushes all entries.
  */
 static bool
-pgstat_flush_pending_entries(bool nowait)
+pgstat_flush_pending_entries(bool nowait, bool anytime_only)
 {
 	bool		have_pending = false;
 	dlist_node *cur = NULL;
@@ -1377,8 +1380,22 @@ pgstat_flush_pending_entries(bool nowait)
 		Assert(!kind_info->fixed_amount);
 		Assert(kind_info->flush_pending_cb != NULL);
 
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+		{
+			have_pending = true;
+
+			if (dlist_has_next(&pgStatPending, cur))
+				next = dlist_next_node(&pgStatPending, cur);
+			else
+				next = NULL;
+
+			cur = next;
+			continue;
+		}
+
 		/* flush the stats, if possible */
-		did_flush = kind_info->flush_pending_cb(entry_ref, nowait);
+		did_flush = kind_info->flush_pending_cb(entry_ref, nowait, anytime_only);
 
 		Assert(did_flush || nowait);
 
@@ -1402,6 +1419,33 @@ pgstat_flush_pending_entries(bool nowait)
 	return have_pending;
 }
 
+/*
+ * Flush fixed-amount stats.
+ *
+ * If anytime_only is true, only flushes FLUSH_ANYTIME stats (safe inside transactions).
+ * If anytime_only is false, flushes all stats with flush_static_cb.
+ */
+static bool
+pgstat_flush_fixed_stats(bool nowait, bool anytime_only)
+{
+	bool		partial_flush = false;
+
+	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 || !kind_info->flush_static_cb)
+			continue;
+
+		/* Skip transactional stats if we're in anytime_only mode */
+		if (anytime_only && kind_info->flush_mode == FLUSH_AT_TXN_BOUNDARY)
+			continue;
+
+		partial_flush |= kind_info->flush_static_cb(nowait, anytime_only);
+	}
+
+	return partial_flush;
+}
 
 /* ------------------------------------------------------------
  * Helper / infrastructure functions
@@ -2119,3 +2163,31 @@ assign_stats_fetch_consistency(int newval, void *extra)
 	if (pgstat_fetch_consistency != newval)
 		force_stats_snapshot_clear = true;
 }
+
+/*
+ * Flushes only FLUSH_ANYTIME stats using non-blocking locks. Transactional
+ * stats (FLUSH_AT_TXN_BOUNDARY) remain pending until transaction boundary.
+ * Safe to call inside transactions.
+ */
+void
+pgstat_report_anytime_stat(bool force)
+{
+	bool		nowait = !force;
+
+	pgstat_assert_is_up();
+
+	/* Flush stats outside of transaction boundary */
+	pgstat_flush_pending_entries(nowait, true);
+	pgstat_flush_fixed_stats(nowait, true);
+}
+
+/*
+ * Timeout handler for flushing non-transactional stats.
+ */
+void
+AnytimeStatsUpdateTimeoutHandler(void)
+{
+	AnytimeStatsUpdateTimeoutPending = true;
+	InterruptPending = true;
+	SetLatch(MyLatch);
+}
diff --git a/src/backend/utils/activity/pgstat_backend.c b/src/backend/utils/activity/pgstat_backend.c
index 1350f5f62f1..b0bd220882d 100644
--- a/src/backend/utils/activity/pgstat_backend.c
+++ b/src/backend/utils/activity/pgstat_backend.c
@@ -31,6 +31,7 @@
 #include "storage/procarray.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 
 /*
  * Backend statistics counts waiting to be flushed out. These counters may be
@@ -66,6 +67,9 @@ pgstat_count_backend_io_op_time(IOObject io_object, IOContext io_context,
 	INSTR_TIME_ADD(PendingBackendStats.pending_io.pending_times[io_object][io_context][io_op],
 				   io_time);
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	backend_has_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -82,6 +86,9 @@ pgstat_count_backend_io_op(IOObject io_object, IOContext io_context,
 	PendingBackendStats.pending_io.counts[io_object][io_context][io_op] += cnt;
 	PendingBackendStats.pending_io.bytes[io_object][io_context][io_op] += bytes;
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	backend_has_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -268,7 +275,7 @@ pgstat_flush_backend_entry_wal(PgStat_EntryRef *entry_ref)
  * if some statistics could not be flushed due to lock contention.
  */
 bool
-pgstat_flush_backend(bool nowait, bits32 flags)
+pgstat_flush_backend(bool nowait, bits32 flags, bool anytime_only)
 {
 	PgStat_EntryRef *entry_ref;
 	bool		has_pending_data = false;
@@ -311,9 +318,9 @@ pgstat_flush_backend(bool nowait, bits32 flags)
  * If some stats could not be flushed due to lock contention, return true.
  */
 bool
-pgstat_backend_flush_cb(bool nowait)
+pgstat_backend_flush_cb(bool nowait, bool anytime_only)
 {
-	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL);
+	return pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_ALL, anytime_only);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_bgwriter.c b/src/backend/utils/activity/pgstat_bgwriter.c
index ed2fd801189..1c5f0c3ec40 100644
--- a/src/backend/utils/activity/pgstat_bgwriter.c
+++ b/src/backend/utils/activity/pgstat_bgwriter.c
@@ -61,7 +61,7 @@ pgstat_report_bgwriter(void)
 	/*
 	 * Report IO statistics
 	 */
-	pgstat_flush_io(false);
+	pgstat_flush_io(false, true);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_checkpointer.c b/src/backend/utils/activity/pgstat_checkpointer.c
index 1f70194b7a7..2d89a082464 100644
--- a/src/backend/utils/activity/pgstat_checkpointer.c
+++ b/src/backend/utils/activity/pgstat_checkpointer.c
@@ -68,7 +68,7 @@ pgstat_report_checkpointer(void)
 	/*
 	 * Report IO statistics
 	 */
-	pgstat_flush_io(false);
+	pgstat_flush_io(false, true);
 }
 
 /*
diff --git a/src/backend/utils/activity/pgstat_database.c b/src/backend/utils/activity/pgstat_database.c
index d7f6d4c5ee6..61094f96a6c 100644
--- a/src/backend/utils/activity/pgstat_database.c
+++ b/src/backend/utils/activity/pgstat_database.c
@@ -425,7 +425,7 @@ pgstat_reset_database_timestamp(Oid dboid, TimestampTz ts)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStatShared_Database *sharedent;
 	PgStat_StatDBEntry *pendingent;
diff --git a/src/backend/utils/activity/pgstat_function.c b/src/backend/utils/activity/pgstat_function.c
index e6b84283c6c..5ba4958382f 100644
--- a/src/backend/utils/activity/pgstat_function.c
+++ b/src/backend/utils/activity/pgstat_function.c
@@ -190,11 +190,13 @@ pgstat_end_function_usage(PgStat_FunctionCallUsage *fcu, bool finalize)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_FunctionCounts *localent;
 	PgStatShared_Function *shfuncent;
 
+	Assert(!anytime_only);
+
 	localent = (PgStat_FunctionCounts *) entry_ref->pending;
 	shfuncent = (PgStatShared_Function *) entry_ref->shared_stats;
 
diff --git a/src/backend/utils/activity/pgstat_io.c b/src/backend/utils/activity/pgstat_io.c
index 28de24538dc..7cd32900236 100644
--- a/src/backend/utils/activity/pgstat_io.c
+++ b/src/backend/utils/activity/pgstat_io.c
@@ -19,6 +19,7 @@
 #include "executor/instrument.h"
 #include "storage/bufmgr.h"
 #include "utils/pgstat_internal.h"
+#include "utils/timeout.h"
 
 static PgStat_PendingIO PendingIOStats;
 static bool have_iostats = false;
@@ -79,6 +80,9 @@ pgstat_count_io_op(IOObject io_object, IOContext io_context, IOOp io_op,
 	/* Add the per-backend counts */
 	pgstat_count_backend_io_op(io_object, io_context, io_op, cnt, bytes);
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	have_iostats = true;
 	pgstat_report_fixed = true;
 }
@@ -172,9 +176,9 @@ pgstat_fetch_stat_io(void)
  * Simpler wrapper of pgstat_io_flush_cb()
  */
 void
-pgstat_flush_io(bool nowait)
+pgstat_flush_io(bool nowait, bool anytime_only)
 {
-	(void) pgstat_io_flush_cb(nowait);
+	(void) pgstat_io_flush_cb(nowait, anytime_only);
 }
 
 /*
@@ -186,7 +190,7 @@ pgstat_flush_io(bool nowait)
  * acquired. Otherwise, return false.
  */
 bool
-pgstat_io_flush_cb(bool nowait)
+pgstat_io_flush_cb(bool nowait, bool anytime_only)
 {
 	LWLock	   *bktype_lock;
 	PgStat_BktypeIO *bktype_shstats;
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..04d21483d93 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -267,8 +267,8 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	 * is done -- which will likely vacuum many relations -- or until the
 	 * VACUUM command has processed all tables and committed.
 	 */
-	pgstat_flush_io(false);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(false, true);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -362,8 +362,8 @@ pgstat_report_analyze(Relation rel,
 	pgstat_unlock_entry(entry_ref);
 
 	/* see pgstat_report_vacuum() */
-	pgstat_flush_io(false);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(false, true);
+	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -812,7 +812,7 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
  * entry when successfully flushing.
  */
 bool
-pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	Oid			dboid;
 	PgStat_TableStatus *lstats; /* pending stats entry  */
@@ -820,6 +820,8 @@ pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
 	PgStat_StatTabEntry *tabentry;	/* table entry of shared stats */
 	PgStat_StatDBEntry *dbentry;	/* pending database entry */
 
+	Assert(!anytime_only);
+
 	dboid = entry_ref->shared_entry->key.dboid;
 	lstats = (PgStat_TableStatus *) entry_ref->pending;
 	shtabstats = (PgStatShared_Relation *) entry_ref->shared_stats;
diff --git a/src/backend/utils/activity/pgstat_slru.c b/src/backend/utils/activity/pgstat_slru.c
index 2190f388eae..bf8a4d58673 100644
--- a/src/backend/utils/activity/pgstat_slru.c
+++ b/src/backend/utils/activity/pgstat_slru.c
@@ -19,6 +19,7 @@
 
 #include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
+#include "utils/timeout.h"
 
 
 static inline PgStat_SLRUStats *get_slru_entry(int slru_idx);
@@ -139,7 +140,7 @@ pgstat_get_slru_index(const char *name)
  * acquired. Otherwise return false.
  */
 bool
-pgstat_slru_flush_cb(bool nowait)
+pgstat_slru_flush_cb(bool nowait, bool anytime_only)
 {
 	PgStatShared_SLRU *stats_shmem = &pgStatLocal.shmem->slru;
 	int			i;
@@ -223,6 +224,9 @@ get_slru_entry(int slru_idx)
 
 	Assert((slru_idx >= 0) && (slru_idx < SLRU_NUM_ELEMENTS));
 
+	/* Schedule next anytime stats update timeout */
+	pgstat_schedule_anytime_update();
+
 	have_slrustats = true;
 	pgstat_report_fixed = true;
 
diff --git a/src/backend/utils/activity/pgstat_subscription.c b/src/backend/utils/activity/pgstat_subscription.c
index 500b1899188..c4614817966 100644
--- a/src/backend/utils/activity/pgstat_subscription.c
+++ b/src/backend/utils/activity/pgstat_subscription.c
@@ -116,11 +116,13 @@ pgstat_fetch_stat_subscription(Oid subid)
  * false without flushing the entry.  Otherwise returns true.
  */
 bool
-pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait)
+pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_BackendSubEntry *localent;
 	PgStatShared_Subscription *shsubent;
 
+	Assert(!anytime_only);
+
 	localent = (PgStat_BackendSubEntry *) entry_ref->pending;
 	shsubent = (PgStatShared_Subscription *) entry_ref->shared_stats;
 
diff --git a/src/backend/utils/activity/pgstat_wal.c b/src/backend/utils/activity/pgstat_wal.c
index 183e0a7a97b..eb5f8f46925 100644
--- a/src/backend/utils/activity/pgstat_wal.c
+++ b/src/backend/utils/activity/pgstat_wal.c
@@ -51,12 +51,12 @@ pgstat_report_wal(bool force)
 	nowait = !force;
 
 	/* flush wal stats */
-	(void) pgstat_wal_flush_cb(nowait);
-	pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_WAL);
+	(void) pgstat_wal_flush_cb(nowait, true);
+	pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_WAL, true);
 
 	/* flush IO stats */
-	pgstat_flush_io(nowait);
-	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_IO);
+	pgstat_flush_io(nowait, true);
+	(void) pgstat_flush_backend(nowait, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -88,7 +88,7 @@ pgstat_wal_have_pending(void)
  * acquired. Otherwise return false.
  */
 bool
-pgstat_wal_flush_cb(bool nowait)
+pgstat_wal_flush_cb(bool nowait, bool anytime_only)
 {
 	PgStatShared_Wal *stats_shmem = &pgStatLocal.shmem->wal;
 	WalUsage	wal_usage_diff = {0};
diff --git a/src/backend/utils/init/globals.c b/src/backend/utils/init/globals.c
index 36ad708b360..ad44826c39e 100644
--- a/src/backend/utils/init/globals.c
+++ b/src/backend/utils/init/globals.c
@@ -40,6 +40,7 @@ volatile sig_atomic_t IdleSessionTimeoutPending = false;
 volatile sig_atomic_t ProcSignalBarrierPending = false;
 volatile sig_atomic_t LogMemoryContextPending = false;
 volatile sig_atomic_t IdleStatsUpdateTimeoutPending = false;
+volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending = false;
 volatile uint32 InterruptHoldoffCount = 0;
 volatile uint32 QueryCancelHoldoffCount = 0;
 volatile uint32 CritSectionCount = 0;
diff --git a/src/backend/utils/init/postinit.c b/src/backend/utils/init/postinit.c
index 3f401faf3de..f45365f47f7 100644
--- a/src/backend/utils/init/postinit.c
+++ b/src/backend/utils/init/postinit.c
@@ -64,6 +64,7 @@
 #include "utils/injection_point.h"
 #include "utils/memutils.h"
 #include "utils/pg_locale.h"
+#include "utils/pgstat_internal.h"
 #include "utils/portal.h"
 #include "utils/ps_status.h"
 #include "utils/snapmgr.h"
@@ -765,6 +766,8 @@ InitPostgres(const char *in_dbname, Oid dboid,
 		RegisterTimeout(CLIENT_CONNECTION_CHECK_TIMEOUT, ClientCheckTimeoutHandler);
 		RegisterTimeout(IDLE_STATS_UPDATE_TIMEOUT,
 						IdleStatsUpdateTimeoutHandler);
+		RegisterTimeout(ANYTIME_STATS_UPDATE_TIMEOUT,
+						AnytimeStatsUpdateTimeoutHandler);
 	}
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index db559b39c4d..8aeb9628871 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -96,6 +96,7 @@ extern PGDLLIMPORT volatile sig_atomic_t IdleSessionTimeoutPending;
 extern PGDLLIMPORT volatile sig_atomic_t ProcSignalBarrierPending;
 extern PGDLLIMPORT volatile sig_atomic_t LogMemoryContextPending;
 extern PGDLLIMPORT volatile sig_atomic_t IdleStatsUpdateTimeoutPending;
+extern PGDLLIMPORT volatile sig_atomic_t AnytimeStatsUpdateTimeoutPending;
 
 extern PGDLLIMPORT volatile sig_atomic_t CheckClientConnectionPending;
 extern PGDLLIMPORT volatile sig_atomic_t ClientConnectionLost;
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index fff7ecc2533..b340a680614 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -35,6 +35,9 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/* Minimum interval non-forced stats flushes */
+#define PGSTAT_MIN_INTERVAL	1000
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -533,8 +536,21 @@ extern void pgstat_initialize(void);
 
 /* Functions called from backends */
 extern long pgstat_report_stat(bool force);
+extern void pgstat_report_anytime_stat(bool force);
 extern void pgstat_force_next_flush(void);
 
+/*
+ * Schedule the next anytime stats update timeout.
+ *
+ * This should be called whenever accumulating statistics that support
+ * FLUSH_ANYTIME flushing mode.
+ */
+#define pgstat_schedule_anytime_update()												\
+	do {																				\
+		if (IsUnderPostmaster && !get_timeout_active(ANYTIME_STATS_UPDATE_TIMEOUT))		\
+			enable_timeout_after(ANYTIME_STATS_UPDATE_TIMEOUT, PGSTAT_MIN_INTERVAL);	\
+	} while (0)
+
 extern void pgstat_reset_counters(void);
 extern void pgstat_reset(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_reset_of_kind(PgStat_Kind kind);
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 9b8fbae00ed..607f4255268 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -224,6 +224,19 @@ typedef struct PgStat_SubXactStatus
 	PgStat_TableXactStatus *first;	/* head of list for this subxact */
 } PgStat_SubXactStatus;
 
+/*
+ * Flush mode for statistics kinds.
+ *
+ * FLUSH_AT_TXN_BOUNDARY has to be the first because we want it to be the
+ * default value.
+ */
+typedef enum PgStat_FlushMode
+{
+	FLUSH_AT_TXN_BOUNDARY,		/* All fields can only be flushed at
+								 * transaction boundary */
+	FLUSH_ANYTIME,				/* All fields can be flushed anytime,
+								 * including within transactions */
+} PgStat_FlushMode;
 
 /*
  * Metadata for a specific kind of statistics.
@@ -251,6 +264,16 @@ typedef struct PgStat_KindInfo
 	 */
 	bool		track_entry_count:1;
 
+	/*
+	 * The mode of when to flush stats. See PgStat_FlushMode for more details.
+	 *
+	 * This member only has meaning for statistics kinds that accumulate
+	 * pending stats and use flush callbacks. For kinds that write directly to
+	 * shared memory (e.g., archiver, bgwriter, checkpointer), this member has
+	 * no effect.
+	 */
+	PgStat_FlushMode flush_mode;
+
 	/*
 	 * The size of an entry in the shared stats hash table (pointed to by
 	 * PgStatShared_HashEntry->body).  For fixed-numbered statistics, this is
@@ -297,8 +320,10 @@ typedef struct PgStat_KindInfo
 	 * For variable-numbered stats: flush pending stats. Required if pending
 	 * data is used. See flush_static_cb when dealing with stats data that
 	 * that cannot use PgStat_EntryRef->pending.
+	 *
+	 * The anytime_only parameter indicates whether this is an anytime flush.
 	 */
-	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait);
+	bool		(*flush_pending_cb) (PgStat_EntryRef *sr, bool nowait, bool anytime_only);
 
 	/*
 	 * For variable-numbered stats: delete pending stats. Optional.
@@ -366,8 +391,10 @@ typedef struct PgStat_KindInfo
 	 *
 	 * "pgstat_report_fixed" needs to be set to trigger the flush of pending
 	 * stats.
+	 *
+	 * The anytime_only parameter indicates whether this is an anytime flush.
 	 */
-	bool		(*flush_static_cb) (bool nowait);
+	bool		(*flush_static_cb) (bool nowait, bool anytime_only);
 
 	/*
 	 * For fixed-numbered statistics: Reset All.
@@ -677,6 +704,7 @@ extern PgStat_EntryRef *pgstat_fetch_pending_entry(PgStat_Kind kind,
 
 extern void *pgstat_fetch_entry(PgStat_Kind kind, Oid dboid, uint64 objid);
 extern void pgstat_snapshot_fixed(PgStat_Kind kind);
+extern void AnytimeStatsUpdateTimeoutHandler(void);
 
 
 /*
@@ -696,8 +724,8 @@ extern void pgstat_archiver_snapshot_cb(void);
 #define PGSTAT_BACKEND_FLUSH_WAL   (1 << 1) /* Flush WAL statistics */
 #define PGSTAT_BACKEND_FLUSH_ALL   (PGSTAT_BACKEND_FLUSH_IO | PGSTAT_BACKEND_FLUSH_WAL)
 
-extern bool pgstat_flush_backend(bool nowait, bits32 flags);
-extern bool pgstat_backend_flush_cb(bool nowait);
+extern bool pgstat_flush_backend(bool nowait, bits32 flags, bool anytime_only);
+extern bool pgstat_backend_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_backend_reset_timestamp_cb(PgStatShared_Common *header,
 											  TimestampTz ts);
 
@@ -729,7 +757,7 @@ extern void AtEOXact_PgStat_Database(bool isCommit, bool parallel);
 
 extern PgStat_StatDBEntry *pgstat_prep_database_pending(Oid dboid);
 extern void pgstat_reset_database_timestamp(Oid dboid, TimestampTz ts);
-extern bool pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_database_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_database_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
@@ -737,7 +765,7 @@ extern void pgstat_database_reset_timestamp_cb(PgStatShared_Common *header, Time
  * Functions in pgstat_function.c
  */
 
-extern bool pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_function_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_function_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
@@ -745,9 +773,9 @@ extern void pgstat_function_reset_timestamp_cb(PgStatShared_Common *header, Time
  * Functions in pgstat_io.c
  */
 
-extern void pgstat_flush_io(bool nowait);
+extern void pgstat_flush_io(bool nowait, bool anytime_only);
 
-extern bool pgstat_io_flush_cb(bool nowait);
+extern bool pgstat_io_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_io_init_shmem_cb(void *stats);
 extern void pgstat_io_reset_all_cb(TimestampTz ts);
 extern void pgstat_io_snapshot_cb(void);
@@ -762,7 +790,7 @@ extern void AtEOSubXact_PgStat_Relations(PgStat_SubXactStatus *xact_state, bool
 extern void AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 
-extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
@@ -809,7 +837,7 @@ extern PgStatShared_Common *pgstat_init_entry(PgStat_Kind kind,
  * Functions in pgstat_slru.c
  */
 
-extern bool pgstat_slru_flush_cb(bool nowait);
+extern bool pgstat_slru_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_slru_init_shmem_cb(void *stats);
 extern void pgstat_slru_reset_all_cb(TimestampTz ts);
 extern void pgstat_slru_snapshot_cb(void);
@@ -820,7 +848,7 @@ extern void pgstat_slru_snapshot_cb(void);
  */
 
 extern void pgstat_wal_init_backend_cb(void);
-extern bool pgstat_wal_flush_cb(bool nowait);
+extern bool pgstat_wal_flush_cb(bool nowait, bool anytime_only);
 extern void pgstat_wal_init_shmem_cb(void *stats);
 extern void pgstat_wal_reset_all_cb(TimestampTz ts);
 extern void pgstat_wal_snapshot_cb(void);
@@ -830,7 +858,7 @@ extern void pgstat_wal_snapshot_cb(void);
  * Functions in pgstat_subscription.c
  */
 
-extern bool pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
+extern bool pgstat_subscription_flush_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only);
 extern void pgstat_subscription_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
 
 
diff --git a/src/include/utils/timeout.h b/src/include/utils/timeout.h
index 0965b590b34..10723bb664c 100644
--- a/src/include/utils/timeout.h
+++ b/src/include/utils/timeout.h
@@ -35,6 +35,7 @@ typedef enum TimeoutId
 	IDLE_SESSION_TIMEOUT,
 	IDLE_STATS_UPDATE_TIMEOUT,
 	CLIENT_CONNECTION_CHECK_TIMEOUT,
+	ANYTIME_STATS_UPDATE_TIMEOUT,
 	STARTUP_PROGRESS_TIMEOUT,
 	/* First user-definable timeout reason */
 	USER_TIMEOUT,
diff --git a/src/test/modules/test_custom_stats/test_custom_var_stats.c b/src/test/modules/test_custom_stats/test_custom_var_stats.c
index 64a8fe63cce..bc0b5d6e0eb 100644
--- a/src/test/modules/test_custom_stats/test_custom_var_stats.c
+++ b/src/test/modules/test_custom_stats/test_custom_var_stats.c
@@ -83,7 +83,7 @@ static dsa_area *custom_stats_description_dsa = NULL;
 
 /* Flush callback: merge pending stats into shared memory */
 static bool test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref,
-												   bool nowait);
+												   bool nowait, bool anytime_only);
 
 /* Serialization callback: write auxiliary entry data */
 static void test_custom_stats_var_to_serialized_data(const PgStat_HashKey *key,
@@ -150,7 +150,7 @@ _PG_init(void)
  * Returns false only if nowait=true and lock acquisition fails.
  */
 static bool
-test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref, bool nowait)
+test_custom_stats_var_flush_pending_cb(PgStat_EntryRef *entry_ref, bool nowait, bool anytime_only)
 {
 	PgStat_StatCustomVarEntry *pending_entry;
 	PgStatShared_CustomVarEntry *shared_entry;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 9f5ee8fd482..860f835c088 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2268,6 +2268,7 @@ PgStat_Counter
 PgStat_EntryRef
 PgStat_EntryRefHashEntry
 PgStat_FetchConsistency
+PgStat_FlushMode
 PgStat_FunctionCallUsage
 PgStat_FunctionCounts
 PgStat_HashKey
-- 
2.34.1


--DxqFthphbM+ha9Dy
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v6-0002-Add-anytime-flush-tests-for-custom-stats.patch"



^ permalink  raw  reply  [nested|flat] 12+ messages in thread


end of thread, other threads:[~2026-01-05 09:41 UTC | newest]

Thread overview: 12+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2019-06-13 13:04 [PATCH] Implementation of Index Skip Scan (see Loose Index Scan in the wiki [1]) on top of IndexOnlyScan. To make it suitable for both situations when there are small number of distinct values and significant amount of distinct values the following approach is taken - instead of searching from the root for every value we're searching for then first on the current page, and then if not found continue searching from the root. jesperpedersen <[email protected]>
2026-01-05 09:41 [PATCH v8 1/5] Add pgstat_report_anytime_stat() for periodic stats flushing Bertrand Drouvot <[email protected]>
2026-01-05 09:41 [PATCH v9 1/5] Add pgstat_report_anytime_stat() for periodic stats flushing Bertrand Drouvot <[email protected]>
2026-01-05 09:41 [PATCH v11 1/5] Add pgstat_report_anytime_stat() for periodic stats flushing Bertrand Drouvot <[email protected]>
2026-01-05 09:41 [PATCH v1 1/3] Add pgstat_report_anytime_stat() for periodic stats flushing Bertrand Drouvot <[email protected]>
2026-01-05 09:41 [PATCH v2 1/3] Add pgstat_report_anytime_stat() for periodic stats flushing Bertrand Drouvot <[email protected]>
2026-01-05 09:41 [PATCH v7 1/5] Add pgstat_report_anytime_stat() for periodic stats flushing Bertrand Drouvot <[email protected]>
2026-01-05 09:41 [PATCH v10 1/5] Add pgstat_report_anytime_stat() for periodic stats flushing Bertrand Drouvot <[email protected]>
2026-01-05 09:41 [PATCH v3 1/3] Add pgstat_report_anytime_stat() for periodic stats flushing Bertrand Drouvot <[email protected]>
2026-01-05 09:41 [PATCH v4 1/4] Add pgstat_report_anytime_stat() for periodic stats flushing Bertrand Drouvot <[email protected]>
2026-01-05 09:41 [PATCH v5 1/4] Add pgstat_report_anytime_stat() for periodic stats flushing Bertrand Drouvot <[email protected]>
2026-01-05 09:41 [PATCH v6 1/5] Add pgstat_report_anytime_stat() for periodic stats flushing Bertrand Drouvot <[email protected]>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox