agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v17 2/8] Row pattern recognition patch (parse/analysis).
12+ messages / 2 participants
[nested] [flat]

* [PATCH v17 2/8] Row pattern recognition patch (parse/analysis).
@ 2024-04-28 11:00  Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Tatsuo Ishii @ 2024-04-28 11:00 UTC (permalink / raw)

---
 src/backend/parser/parse_agg.c    |   7 +
 src/backend/parser/parse_clause.c | 296 +++++++++++++++++++++++++++++-
 src/backend/parser/parse_expr.c   |   4 +
 src/backend/parser/parse_func.c   |   3 +
 4 files changed, 309 insertions(+), 1 deletion(-)

diff --git a/src/backend/parser/parse_agg.c b/src/backend/parser/parse_agg.c
index bee7d8346a..9bc22a836a 100644
--- a/src/backend/parser/parse_agg.c
+++ b/src/backend/parser/parse_agg.c
@@ -577,6 +577,10 @@ check_agglevels_and_constraints(ParseState *pstate, Node *expr)
 			errkind = true;
 			break;
 
+		case EXPR_KIND_RPR_DEFINE:
+			errkind = true;
+			break;
+
 			/*
 			 * There is intentionally no default: case here, so that the
 			 * compiler will warn if we add a new ParseExprKind without
@@ -967,6 +971,9 @@ transformWindowFuncCall(ParseState *pstate, WindowFunc *wfunc,
 		case EXPR_KIND_CYCLE_MARK:
 			errkind = true;
 			break;
+		case EXPR_KIND_RPR_DEFINE:
+			errkind = true;
+			break;
 
 			/*
 			 * There is intentionally no default: case here, so that the
diff --git a/src/backend/parser/parse_clause.c b/src/backend/parser/parse_clause.c
index 4fc5fc87e0..003a1e14ce 100644
--- a/src/backend/parser/parse_clause.c
+++ b/src/backend/parser/parse_clause.c
@@ -98,7 +98,14 @@ static WindowClause *findWindowClause(List *wclist, const char *name);
 static Node *transformFrameOffset(ParseState *pstate, int frameOptions,
 								  Oid rangeopfamily, Oid rangeopcintype, Oid *inRangeFunc,
 								  Node *clause);
-
+static void transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef,
+						 List **targetlist);
+static List *transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef,
+								   List **targetlist);
+static void transformPatternClause(ParseState *pstate, WindowClause *wc,
+								   WindowDef *windef);
+static List *transformMeasureClause(ParseState *pstate, WindowClause *wc,
+									WindowDef *windef);
 
 /*
  * transformFromClause -
@@ -2956,6 +2963,10 @@ transformWindowDefinitions(ParseState *pstate,
 											 rangeopfamily, rangeopcintype,
 											 &wc->endInRangeFunc,
 											 windef->endOffset);
+
+		/* Process Row Pattern Recognition related clauses */
+		transformRPR(pstate, wc, windef, targetlist);
+
 		wc->runCondition = NIL;
 		wc->winref = winref;
 
@@ -3821,3 +3832,286 @@ transformFrameOffset(ParseState *pstate, int frameOptions,
 
 	return node;
 }
+
+/*
+ * transformRPR
+ *		Process Row Pattern Recognition related clauses
+ */
+static void
+transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef,
+			 List **targetlist)
+{
+	/*
+	 * Window definition exists?
+	 */
+	if (windef == NULL)
+		return;
+
+	/*
+	 * Row Pattern Common Syntax clause exists?
+	 */
+	if (windef->rpCommonSyntax == NULL)
+		return;
+
+	/* Check Frame option. Frame must start at current row */
+	if ((wc->frameOptions & FRAMEOPTION_START_CURRENT_ROW) == 0)
+		ereport(ERROR,
+				(errcode(ERRCODE_SYNTAX_ERROR),
+				 errmsg("FRAME must start at current row when row patttern recognition is used")));
+
+	/* Transform AFTER MACH SKIP TO clause */
+	wc->rpSkipTo = windef->rpCommonSyntax->rpSkipTo;
+
+	/* Transform AFTER MACH SKIP TO variable */
+	wc->rpSkipVariable = windef->rpCommonSyntax->rpSkipVariable;
+
+	/* Transform SEEK or INITIAL clause */
+	wc->initial = windef->rpCommonSyntax->initial;
+
+	/* Transform DEFINE clause into list of TargetEntry's */
+	wc->defineClause = transformDefineClause(pstate, wc, windef, targetlist);
+
+	/* Check PATTERN clause and copy to patternClause */
+	transformPatternClause(pstate, wc, windef);
+
+	/* Transform MEASURE clause */
+	transformMeasureClause(pstate, wc, windef);
+}
+
+/*
+ * transformDefineClause Process DEFINE clause and transform ResTarget into
+ *		list of TargetEntry.
+ *
+ * XXX we only support column reference in row pattern definition search
+ * condition, e.g. "price". <row pattern definition variable name>.<column
+ * reference> is not supported, e.g. "A.price".
+ */
+static List *
+transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef,
+					  List **targetlist)
+{
+	/* DEFINE variable name initials */
+	static char *defineVariableInitials = "abcdefghijklmnopqrstuvwxyz";
+
+	ListCell   *lc,
+			   *l;
+	ResTarget  *restarget,
+			   *r;
+	List	   *restargets;
+	List	   *defineClause;
+	char	   *name;
+	int			initialLen;
+	int			i;
+
+	/*
+	 * If Row Definition Common Syntax exists, DEFINE clause must exist. (the
+	 * raw parser should have already checked it.)
+	 */
+	Assert(windef->rpCommonSyntax->rpDefs != NULL);
+
+	/*
+	 * Check and add "A AS A IS TRUE" if pattern variable is missing in DEFINE
+	 * per the SQL standard.
+	 */
+	restargets = NIL;
+	foreach(lc, windef->rpCommonSyntax->rpPatterns)
+	{
+		A_Expr	   *a;
+		bool		found = false;
+
+		if (!IsA(lfirst(lc), A_Expr))
+			ereport(ERROR,
+					errmsg("node type is not A_Expr"));
+
+		a = (A_Expr *) lfirst(lc);
+		name = strVal(a->lexpr);
+
+		foreach(l, windef->rpCommonSyntax->rpDefs)
+		{
+			restarget = (ResTarget *) lfirst(l);
+
+			if (!strcmp(restarget->name, name))
+			{
+				found = true;
+				break;
+			}
+		}
+
+		if (!found)
+		{
+			/*
+			 * "name" is missing. So create "name AS name IS TRUE" ResTarget
+			 * node and add it to the temporary list.
+			 */
+			A_Const    *n;
+
+			restarget = makeNode(ResTarget);
+			n = makeNode(A_Const);
+			n->val.boolval.type = T_Boolean;
+			n->val.boolval.boolval = true;
+			n->location = -1;
+			restarget->name = pstrdup(name);
+			restarget->indirection = NIL;
+			restarget->val = (Node *) n;
+			restarget->location = -1;
+			restargets = lappend((List *) restargets, restarget);
+		}
+	}
+
+	if (list_length(restargets) >= 1)
+	{
+		/* add missing DEFINEs */
+		windef->rpCommonSyntax->rpDefs =
+			list_concat(windef->rpCommonSyntax->rpDefs, restargets);
+		list_free(restargets);
+	}
+
+	/*
+	 * Check for duplicate row pattern definition variables.  The standard
+	 * requires that no two row pattern definition variable names shall be
+	 * equivalent.
+	 */
+	restargets = NIL;
+	foreach(lc, windef->rpCommonSyntax->rpDefs)
+	{
+		restarget = (ResTarget *) lfirst(lc);
+		name = restarget->name;
+
+		/*
+		 * Add DEFINE expression (Restarget->val) to the targetlist as a
+		 * TargetEntry if it does not exist yet. Planner will add the column
+		 * ref var node to the outer plan's target list later on. This makes
+		 * DEFINE expression could access the outer tuple while evaluating
+		 * PATTERN.
+		 *
+		 * XXX: adding whole expressions of DEFINE to the plan.targetlist is
+		 * not so good, because it's not necessary to evalute the expression
+		 * in the target list while running the plan. We should extract the
+		 * var nodes only then add them to the plan.targetlist.
+		 */
+		findTargetlistEntrySQL99(pstate, (Node *) restarget->val,
+								 targetlist, EXPR_KIND_RPR_DEFINE);
+
+		/*
+		 * Make sure that the row pattern definition search condition is a
+		 * boolean expression.
+		 */
+		transformWhereClause(pstate, restarget->val,
+							 EXPR_KIND_RPR_DEFINE, "DEFINE");
+
+		foreach(l, restargets)
+		{
+			char	   *n;
+
+			r = (ResTarget *) lfirst(l);
+			n = r->name;
+
+			if (!strcmp(n, name))
+				ereport(ERROR,
+						(errcode(ERRCODE_SYNTAX_ERROR),
+						 errmsg("row pattern definition variable name \"%s\" appears more than once in DEFINE clause",
+								name),
+						 parser_errposition(pstate, exprLocation((Node *) r))));
+		}
+		restargets = lappend(restargets, restarget);
+	}
+	list_free(restargets);
+
+	/*
+	 * Create list of row pattern DEFINE variable name's initial. We assign
+	 * [a-z] to them (up to 26 variable names are allowed).
+	 */
+	restargets = NIL;
+	i = 0;
+	initialLen = strlen(defineVariableInitials);
+
+	foreach(lc, windef->rpCommonSyntax->rpDefs)
+	{
+		char		initial[2];
+
+		restarget = (ResTarget *) lfirst(lc);
+		name = restarget->name;
+
+		if (i >= initialLen)
+		{
+			ereport(ERROR,
+					(errcode(ERRCODE_SYNTAX_ERROR),
+					 errmsg("number of row pattern definition variable names exceeds %d",
+							initialLen),
+					 parser_errposition(pstate,
+										exprLocation((Node *) restarget))));
+		}
+		initial[0] = defineVariableInitials[i++];
+		initial[1] = '\0';
+		wc->defineInitial = lappend(wc->defineInitial,
+									makeString(pstrdup(initial)));
+	}
+
+	defineClause = transformTargetList(pstate, windef->rpCommonSyntax->rpDefs,
+									   EXPR_KIND_RPR_DEFINE);
+
+	/* mark column origins */
+	markTargetListOrigins(pstate, defineClause);
+
+	/* mark all nodes in the DEFINE clause tree with collation information */
+	assign_expr_collations(pstate, (Node *) defineClause);
+
+	return defineClause;
+}
+
+/*
+ * transformPatternClause
+ *		Process PATTERN clause and return PATTERN clause in the raw parse tree
+ */
+static void
+transformPatternClause(ParseState *pstate, WindowClause *wc,
+					   WindowDef *windef)
+{
+	ListCell   *lc;
+
+	/*
+	 * Row Pattern Common Syntax clause exists?
+	 */
+	if (windef->rpCommonSyntax == NULL)
+		return;
+
+	wc->patternVariable = NIL;
+	wc->patternRegexp = NIL;
+	foreach(lc, windef->rpCommonSyntax->rpPatterns)
+	{
+		A_Expr	   *a;
+		char	   *name;
+		char	   *regexp;
+
+		if (!IsA(lfirst(lc), A_Expr))
+			ereport(ERROR,
+					errmsg("node type is not A_Expr"));
+
+		a = (A_Expr *) lfirst(lc);
+		name = strVal(a->lexpr);
+
+		wc->patternVariable = lappend(wc->patternVariable, makeString(pstrdup(name)));
+		regexp = strVal(lfirst(list_head(a->name)));
+
+		wc->patternRegexp = lappend(wc->patternRegexp, makeString(pstrdup(regexp)));
+	}
+}
+
+/*
+ * transformMeasureClause
+ *		Process MEASURE clause
+ *	XXX MEASURE clause is not supported yet
+ */
+static List *
+transformMeasureClause(ParseState *pstate, WindowClause *wc,
+					   WindowDef *windef)
+{
+	if (windef->rowPatternMeasures == NIL)
+		return NIL;
+
+	ereport(ERROR,
+			(errcode(ERRCODE_SYNTAX_ERROR),
+			 errmsg("%s", "MEASURE clause is not supported yet"),
+			 parser_errposition(pstate, exprLocation((Node *) windef->rowPatternMeasures))));
+	return NIL;
+}
diff --git a/src/backend/parser/parse_expr.c b/src/backend/parser/parse_expr.c
index 1c1c86aa3e..5540a0fb0a 100644
--- a/src/backend/parser/parse_expr.c
+++ b/src/backend/parser/parse_expr.c
@@ -578,6 +578,7 @@ transformColumnRef(ParseState *pstate, ColumnRef *cref)
 		case EXPR_KIND_COPY_WHERE:
 		case EXPR_KIND_GENERATED_COLUMN:
 		case EXPR_KIND_CYCLE_MARK:
+		case EXPR_KIND_RPR_DEFINE:
 			/* okay */
 			break;
 
@@ -1817,6 +1818,7 @@ transformSubLink(ParseState *pstate, SubLink *sublink)
 		case EXPR_KIND_VALUES:
 		case EXPR_KIND_VALUES_SINGLE:
 		case EXPR_KIND_CYCLE_MARK:
+		case EXPR_KIND_RPR_DEFINE:
 			/* okay */
 			break;
 		case EXPR_KIND_CHECK_CONSTRAINT:
@@ -3197,6 +3199,8 @@ ParseExprKindName(ParseExprKind exprKind)
 			return "GENERATED AS";
 		case EXPR_KIND_CYCLE_MARK:
 			return "CYCLE";
+		case EXPR_KIND_RPR_DEFINE:
+			return "DEFINE";
 
 			/*
 			 * There is intentionally no default: case here, so that the
diff --git a/src/backend/parser/parse_func.c b/src/backend/parser/parse_func.c
index 0cbc950c95..ad982a7c17 100644
--- a/src/backend/parser/parse_func.c
+++ b/src/backend/parser/parse_func.c
@@ -2657,6 +2657,9 @@ check_srf_call_placement(ParseState *pstate, Node *last_srf, int location)
 		case EXPR_KIND_CYCLE_MARK:
 			errkind = true;
 			break;
+		case EXPR_KIND_RPR_DEFINE:
+			errkind = true;
+			break;
 
 			/*
 			 * There is intentionally no default: case here, so that the
-- 
2.25.1


----Next_Part(Sun_Apr_28_20_28_26_2024_444)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v17-0003-Row-pattern-recognition-patch-rewriter.patch"



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

* [PATCH v5 3/4] Remove useless calls to flush some stats
@ 2026-01-06 11:06  Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-06 11:06 UTC (permalink / raw)

Now that some stats can be flushed outside of transaction boundaries, remove
useless calls to report/flush some stats. Those calls were in place because
before commit <XXXX> stats were flushed only at transaction boundaries.

Note that:

- it reverts 039549d70f6 (it just keeps its tests)
- it can't be done for checkpointer and bgworker for example because they don't
have a flush callback to call
- it can't be done for auxiliary process (walsummarizer for example) because they
currently do not register the new timeout handler
---
 src/backend/replication/walreceiver.c        | 10 ------
 src/backend/replication/walsender.c          | 36 ++------------------
 src/backend/utils/activity/pgstat_relation.c | 13 -------
 src/test/recovery/t/001_stream_rep.pl        |  1 +
 src/test/subscription/t/001_rep_changes.pl   |  1 +
 5 files changed, 4 insertions(+), 57 deletions(-)
  69.9% src/backend/replication/
  22.8% src/backend/utils/activity/
   3.5% src/test/recovery/t/
   3.6% src/test/subscription/t/

diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index 24d7ef795cb..1c5ffcab3e0 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -572,16 +572,6 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 					 */
 					bool		requestReply = false;
 
-					/*
-					 * Report pending statistics to the cumulative stats
-					 * system.  This location is useful for the report as it
-					 * is not within a tight loop in the WAL receiver, to
-					 * avoid bloating pgstats with requests, while also making
-					 * sure that the reports happen each time a status update
-					 * is sent.
-					 */
-					pgstat_report_wal(false);
-
 					/*
 					 * Check if time since last receive from primary has
 					 * reached the configured limit.
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index a0e6a3d200c..74102def9c7 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -94,14 +94,10 @@
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 #include "utils/pg_lsn.h"
-#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
 #include "utils/timeout.h"
 #include "utils/timestamp.h"
 
-/* Minimum interval used by walsender for stats flushes, in ms */
-#define WALSENDER_STATS_FLUSH_INTERVAL         1000
-
 /*
  * Maximum data payload in a WAL data message.  Must be >= XLOG_BLCKSZ.
  *
@@ -1825,7 +1821,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	int			wakeEvents;
 	uint32		wait_event = 0;
 	static XLogRecPtr RecentFlushPtr = InvalidXLogRecPtr;
-	TimestampTz last_flush = 0;
 
 	/*
 	 * Fast path to avoid acquiring the spinlock in case we already know we
@@ -1846,7 +1841,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	{
 		bool		wait_for_standby_at_stop = false;
 		long		sleeptime;
-		TimestampTz now;
 
 		/* Clear any already-pending wakeups */
 		ResetLatch(MyLatch);
@@ -1957,8 +1951,7 @@ WalSndWaitForWal(XLogRecPtr loc)
 		 * new WAL to be generated.  (But if we have nothing to send, we don't
 		 * want to wake on socket-writable.)
 		 */
-		now = GetCurrentTimestamp();
-		sleeptime = WalSndComputeSleeptime(now);
+		sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 		wakeEvents = WL_SOCKET_READABLE;
 
@@ -1967,15 +1960,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 
 		Assert(wait_event != 0);
 
-		/* Report IO statistics, if needed */
-		if (TimestampDifferenceExceeds(last_flush, now,
-									   WALSENDER_STATS_FLUSH_INTERVAL))
-		{
-			pgstat_flush_io(false);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
-			last_flush = now;
-		}
-
 		WalSndWait(wakeEvents, sleeptime, wait_event);
 	}
 
@@ -2878,8 +2862,6 @@ WalSndCheckTimeOut(void)
 static void
 WalSndLoop(WalSndSendDataCallback send_data)
 {
-	TimestampTz last_flush = 0;
-
 	/*
 	 * Initialize the last reply timestamp. That enables timeout processing
 	 * from hereon.
@@ -2974,9 +2956,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		 * WalSndWaitForWal() handle any other blocking; idle receivers need
 		 * its additional actions.  For physical replication, also block if
 		 * caught up; its send_data does not block.
-		 *
-		 * The IO statistics are reported in WalSndWaitForWal() for the
-		 * logical WAL senders.
 		 */
 		if ((WalSndCaughtUp && send_data != XLogSendLogical &&
 			 !streamingDoneSending) ||
@@ -2984,7 +2963,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		{
 			long		sleeptime;
 			int			wakeEvents;
-			TimestampTz now;
 
 			if (!streamingDoneReceiving)
 				wakeEvents = WL_SOCKET_READABLE;
@@ -2995,21 +2973,11 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			 * Use fresh timestamp, not last_processing, to reduce the chance
 			 * of reaching wal_sender_timeout before sending a keepalive.
 			 */
-			now = GetCurrentTimestamp();
-			sleeptime = WalSndComputeSleeptime(now);
+			sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 			if (pq_is_send_pending())
 				wakeEvents |= WL_SOCKET_WRITEABLE;
 
-			/* Report IO statistics, if needed */
-			if (TimestampDifferenceExceeds(last_flush, now,
-										   WALSENDER_STATS_FLUSH_INTERVAL))
-			{
-				pgstat_flush_io(false);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
-				last_flush = now;
-			}
-
 			/* Sleep until something happens or we time out */
 			WalSndWait(wakeEvents, sleeptime, WAIT_EVENT_WAL_SENDER_MAIN);
 		}
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..feae2ae5f44 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -260,15 +260,6 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/*
-	 * Flush IO statistics now. pgstat_report_stat() will flush IO stats,
-	 * however this will not be called until after an entire autovacuum cycle
-	 * 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);
 }
 
 /*
@@ -360,10 +351,6 @@ 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);
 }
 
 /*
diff --git a/src/test/recovery/t/001_stream_rep.pl b/src/test/recovery/t/001_stream_rep.pl
index e9ac67813c7..c058a5f9b1f 100644
--- a/src/test/recovery/t/001_stream_rep.pl
+++ b/src/test/recovery/t/001_stream_rep.pl
@@ -15,6 +15,7 @@ my $node_primary = PostgreSQL::Test::Cluster->new('primary');
 $node_primary->init(
 	allows_streaming => 1,
 	auth_extra => [ '--create-role' => 'repl_role' ]);
+$node_primary->append_conf('postgresql.conf', "stats_flush_interval= '1s'");
 $node_primary->start;
 my $backup_name = 'my_backup';
 
diff --git a/src/test/subscription/t/001_rep_changes.pl b/src/test/subscription/t/001_rep_changes.pl
index d7e62e4d488..dda872f7074 100644
--- a/src/test/subscription/t/001_rep_changes.pl
+++ b/src/test/subscription/t/001_rep_changes.pl
@@ -11,6 +11,7 @@ use Test::More;
 # Initialize publisher node
 my $node_publisher = PostgreSQL::Test::Cluster->new('publisher');
 $node_publisher->init(allows_streaming => 'logical');
+$node_publisher->append_conf('postgresql.conf', "stats_flush_interval= '1s'");
 $node_publisher->start;
 
 # Create subscriber node
-- 
2.34.1


--WLtTrIUEfQDmERxy
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0004-Add-FLUSH_MIXED-support-and-implement-it-for-RELA.patch"



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

* [PATCH v6 4/5] Remove useless calls to flush some stats
@ 2026-01-06 11:06  Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-06 11:06 UTC (permalink / raw)

Now that some stats can be flushed outside of transaction boundaries, remove
useless calls to report/flush some stats. Those calls were in place because
before commit <XXXX> stats were flushed only at transaction boundaries.

Note that:

- it reverts 039549d70f6 (it just keeps its tests)
- it can't be done for checkpointer and bgworker for example because they don't
have a flush callback to call
- it can't be done for auxiliary process (walsummarizer for example) because they
currently do not register the new timeout handler
---
 src/backend/replication/walreceiver.c        | 10 ------
 src/backend/replication/walsender.c          | 36 ++------------------
 src/backend/utils/activity/pgstat_relation.c | 13 -------
 src/test/recovery/t/001_stream_rep.pl        |  1 +
 src/test/subscription/t/001_rep_changes.pl   |  1 +
 5 files changed, 4 insertions(+), 57 deletions(-)
  69.4% src/backend/replication/
  23.4% src/backend/utils/activity/
   3.4% src/test/recovery/t/
   3.5% src/test/subscription/t/

diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index 11b7c114d3b..953ba97ed00 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -571,16 +571,6 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 					 */
 					bool		requestReply = false;
 
-					/*
-					 * Report pending statistics to the cumulative stats
-					 * system.  This location is useful for the report as it
-					 * is not within a tight loop in the WAL receiver, to
-					 * avoid bloating pgstats with requests, while also making
-					 * sure that the reports happen each time a status update
-					 * is sent.
-					 */
-					pgstat_report_wal(false);
-
 					/*
 					 * Check if time since last receive from primary has
 					 * reached the configured limit.
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index a7214d0dc6f..9a136e35b48 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -94,14 +94,10 @@
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 #include "utils/pg_lsn.h"
-#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
 #include "utils/timeout.h"
 #include "utils/timestamp.h"
 
-/* Minimum interval used by walsender for stats flushes, in ms */
-#define WALSENDER_STATS_FLUSH_INTERVAL         1000
-
 /*
  * Maximum data payload in a WAL data message.  Must be >= XLOG_BLCKSZ.
  *
@@ -1846,7 +1842,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	int			wakeEvents;
 	uint32		wait_event = 0;
 	static XLogRecPtr RecentFlushPtr = InvalidXLogRecPtr;
-	TimestampTz last_flush = 0;
 
 	/*
 	 * Fast path to avoid acquiring the spinlock in case we already know we
@@ -1867,7 +1862,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	{
 		bool		wait_for_standby_at_stop = false;
 		long		sleeptime;
-		TimestampTz now;
 
 		/* Clear any already-pending wakeups */
 		ResetLatch(MyLatch);
@@ -1973,8 +1967,7 @@ WalSndWaitForWal(XLogRecPtr loc)
 		 * new WAL to be generated.  (But if we have nothing to send, we don't
 		 * want to wake on socket-writable.)
 		 */
-		now = GetCurrentTimestamp();
-		sleeptime = WalSndComputeSleeptime(now);
+		sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 		wakeEvents = WL_SOCKET_READABLE;
 
@@ -1983,15 +1976,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 
 		Assert(wait_event != 0);
 
-		/* Report IO statistics, if needed */
-		if (TimestampDifferenceExceeds(last_flush, now,
-									   WALSENDER_STATS_FLUSH_INTERVAL))
-		{
-			pgstat_flush_io(false, true);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
-			last_flush = now;
-		}
-
 		WalSndWait(wakeEvents, sleeptime, wait_event);
 	}
 
@@ -2894,8 +2878,6 @@ WalSndCheckTimeOut(void)
 static void
 WalSndLoop(WalSndSendDataCallback send_data)
 {
-	TimestampTz last_flush = 0;
-
 	/*
 	 * Initialize the last reply timestamp. That enables timeout processing
 	 * from hereon.
@@ -2985,9 +2967,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		 * WalSndWaitForWal() handle any other blocking; idle receivers need
 		 * its additional actions.  For physical replication, also block if
 		 * caught up; its send_data does not block.
-		 *
-		 * The IO statistics are reported in WalSndWaitForWal() for the
-		 * logical WAL senders.
 		 */
 		if ((WalSndCaughtUp && send_data != XLogSendLogical &&
 			 !streamingDoneSending) ||
@@ -2995,7 +2974,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		{
 			long		sleeptime;
 			int			wakeEvents;
-			TimestampTz now;
 
 			if (!streamingDoneReceiving)
 				wakeEvents = WL_SOCKET_READABLE;
@@ -3006,21 +2984,11 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			 * Use fresh timestamp, not last_processing, to reduce the chance
 			 * of reaching wal_sender_timeout before sending a keepalive.
 			 */
-			now = GetCurrentTimestamp();
-			sleeptime = WalSndComputeSleeptime(now);
+			sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 			if (pq_is_send_pending())
 				wakeEvents |= WL_SOCKET_WRITEABLE;
 
-			/* Report IO statistics, if needed */
-			if (TimestampDifferenceExceeds(last_flush, now,
-										   WALSENDER_STATS_FLUSH_INTERVAL))
-			{
-				pgstat_flush_io(false, true);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
-				last_flush = now;
-			}
-
 			/* Sleep until something happens or we time out */
 			WalSndWait(wakeEvents, sleeptime, WAIT_EVENT_WAL_SENDER_MAIN);
 		}
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 04d21483d93..ae2952cae89 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -260,15 +260,6 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/*
-	 * Flush IO statistics now. pgstat_report_stat() will flush IO stats,
-	 * however this will not be called until after an entire autovacuum cycle
-	 * is done -- which will likely vacuum many relations -- or until the
-	 * VACUUM command has processed all tables and committed.
-	 */
-	pgstat_flush_io(false, true);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -360,10 +351,6 @@ pgstat_report_analyze(Relation rel,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/* see pgstat_report_vacuum() */
-	pgstat_flush_io(false, true);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
diff --git a/src/test/recovery/t/001_stream_rep.pl b/src/test/recovery/t/001_stream_rep.pl
index e9ac67813c7..c058a5f9b1f 100644
--- a/src/test/recovery/t/001_stream_rep.pl
+++ b/src/test/recovery/t/001_stream_rep.pl
@@ -15,6 +15,7 @@ my $node_primary = PostgreSQL::Test::Cluster->new('primary');
 $node_primary->init(
 	allows_streaming => 1,
 	auth_extra => [ '--create-role' => 'repl_role' ]);
+$node_primary->append_conf('postgresql.conf', "stats_flush_interval= '1s'");
 $node_primary->start;
 my $backup_name = 'my_backup';
 
diff --git a/src/test/subscription/t/001_rep_changes.pl b/src/test/subscription/t/001_rep_changes.pl
index 7d41715ed81..bceec2adede 100644
--- a/src/test/subscription/t/001_rep_changes.pl
+++ b/src/test/subscription/t/001_rep_changes.pl
@@ -11,6 +11,7 @@ use Test::More;
 # Initialize publisher node
 my $node_publisher = PostgreSQL::Test::Cluster->new('publisher');
 $node_publisher->init(allows_streaming => 'logical');
+$node_publisher->append_conf('postgresql.conf', "stats_flush_interval= '1s'");
 $node_publisher->start;
 
 # Create subscriber node
-- 
2.34.1


--DxqFthphbM+ha9Dy
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v6-0005-Change-RELATION-and-DATABASE-stats-to-anytime-flu.patch"



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

* [PATCH v7 4/5] Remove useless calls to flush some stats
@ 2026-01-06 11:06  Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-06 11:06 UTC (permalink / raw)

Now that some stats can be flushed outside of transaction boundaries, remove
useless calls to report/flush some stats. Those calls were in place because
before commit <XXXX> stats were flushed only at transaction boundaries.

Note that:

- it reverts 039549d70f6 (it just keeps its tests)
- it can't be done for checkpointer and bgworker for example because they don't
have a flush callback to call
- it can't be done for auxiliary process (walsummarizer for example) because they
currently do not register the new timeout handler
---
 src/backend/replication/walreceiver.c        | 10 ------
 src/backend/replication/walsender.c          | 36 ++------------------
 src/backend/utils/activity/pgstat_relation.c | 13 -------
 src/test/recovery/t/001_stream_rep.pl        |  1 +
 src/test/subscription/t/001_rep_changes.pl   |  1 +
 5 files changed, 4 insertions(+), 57 deletions(-)
  69.4% src/backend/replication/
  23.4% src/backend/utils/activity/
   3.5% src/test/recovery/t/
   3.6% src/test/subscription/t/

diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index 11b7c114d3b..953ba97ed00 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -571,16 +571,6 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 					 */
 					bool		requestReply = false;
 
-					/*
-					 * Report pending statistics to the cumulative stats
-					 * system.  This location is useful for the report as it
-					 * is not within a tight loop in the WAL receiver, to
-					 * avoid bloating pgstats with requests, while also making
-					 * sure that the reports happen each time a status update
-					 * is sent.
-					 */
-					pgstat_report_wal(false);
-
 					/*
 					 * Check if time since last receive from primary has
 					 * reached the configured limit.
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index a7214d0dc6f..9a136e35b48 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -94,14 +94,10 @@
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 #include "utils/pg_lsn.h"
-#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
 #include "utils/timeout.h"
 #include "utils/timestamp.h"
 
-/* Minimum interval used by walsender for stats flushes, in ms */
-#define WALSENDER_STATS_FLUSH_INTERVAL         1000
-
 /*
  * Maximum data payload in a WAL data message.  Must be >= XLOG_BLCKSZ.
  *
@@ -1846,7 +1842,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	int			wakeEvents;
 	uint32		wait_event = 0;
 	static XLogRecPtr RecentFlushPtr = InvalidXLogRecPtr;
-	TimestampTz last_flush = 0;
 
 	/*
 	 * Fast path to avoid acquiring the spinlock in case we already know we
@@ -1867,7 +1862,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	{
 		bool		wait_for_standby_at_stop = false;
 		long		sleeptime;
-		TimestampTz now;
 
 		/* Clear any already-pending wakeups */
 		ResetLatch(MyLatch);
@@ -1973,8 +1967,7 @@ WalSndWaitForWal(XLogRecPtr loc)
 		 * new WAL to be generated.  (But if we have nothing to send, we don't
 		 * want to wake on socket-writable.)
 		 */
-		now = GetCurrentTimestamp();
-		sleeptime = WalSndComputeSleeptime(now);
+		sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 		wakeEvents = WL_SOCKET_READABLE;
 
@@ -1983,15 +1976,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 
 		Assert(wait_event != 0);
 
-		/* Report IO statistics, if needed */
-		if (TimestampDifferenceExceeds(last_flush, now,
-									   WALSENDER_STATS_FLUSH_INTERVAL))
-		{
-			pgstat_flush_io(false, true);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
-			last_flush = now;
-		}
-
 		WalSndWait(wakeEvents, sleeptime, wait_event);
 	}
 
@@ -2894,8 +2878,6 @@ WalSndCheckTimeOut(void)
 static void
 WalSndLoop(WalSndSendDataCallback send_data)
 {
-	TimestampTz last_flush = 0;
-
 	/*
 	 * Initialize the last reply timestamp. That enables timeout processing
 	 * from hereon.
@@ -2985,9 +2967,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		 * WalSndWaitForWal() handle any other blocking; idle receivers need
 		 * its additional actions.  For physical replication, also block if
 		 * caught up; its send_data does not block.
-		 *
-		 * The IO statistics are reported in WalSndWaitForWal() for the
-		 * logical WAL senders.
 		 */
 		if ((WalSndCaughtUp && send_data != XLogSendLogical &&
 			 !streamingDoneSending) ||
@@ -2995,7 +2974,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		{
 			long		sleeptime;
 			int			wakeEvents;
-			TimestampTz now;
 
 			if (!streamingDoneReceiving)
 				wakeEvents = WL_SOCKET_READABLE;
@@ -3006,21 +2984,11 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			 * Use fresh timestamp, not last_processing, to reduce the chance
 			 * of reaching wal_sender_timeout before sending a keepalive.
 			 */
-			now = GetCurrentTimestamp();
-			sleeptime = WalSndComputeSleeptime(now);
+			sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 			if (pq_is_send_pending())
 				wakeEvents |= WL_SOCKET_WRITEABLE;
 
-			/* Report IO statistics, if needed */
-			if (TimestampDifferenceExceeds(last_flush, now,
-										   WALSENDER_STATS_FLUSH_INTERVAL))
-			{
-				pgstat_flush_io(false, true);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
-				last_flush = now;
-			}
-
 			/* Sleep until something happens or we time out */
 			WalSndWait(wakeEvents, sleeptime, WAIT_EVENT_WAL_SENDER_MAIN);
 		}
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 04d21483d93..ae2952cae89 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -260,15 +260,6 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/*
-	 * Flush IO statistics now. pgstat_report_stat() will flush IO stats,
-	 * however this will not be called until after an entire autovacuum cycle
-	 * is done -- which will likely vacuum many relations -- or until the
-	 * VACUUM command has processed all tables and committed.
-	 */
-	pgstat_flush_io(false, true);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -360,10 +351,6 @@ pgstat_report_analyze(Relation rel,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/* see pgstat_report_vacuum() */
-	pgstat_flush_io(false, true);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
diff --git a/src/test/recovery/t/001_stream_rep.pl b/src/test/recovery/t/001_stream_rep.pl
index e9ac67813c7..cfa095ff0a8 100644
--- a/src/test/recovery/t/001_stream_rep.pl
+++ b/src/test/recovery/t/001_stream_rep.pl
@@ -15,6 +15,7 @@ my $node_primary = PostgreSQL::Test::Cluster->new('primary');
 $node_primary->init(
 	allows_streaming => 1,
 	auth_extra => [ '--create-role' => 'repl_role' ]);
+$node_primary->append_conf('postgresql.conf', "stats_flush_interval = '1s'");
 $node_primary->start;
 my $backup_name = 'my_backup';
 
diff --git a/src/test/subscription/t/001_rep_changes.pl b/src/test/subscription/t/001_rep_changes.pl
index 7d41715ed81..29bae5e1121 100644
--- a/src/test/subscription/t/001_rep_changes.pl
+++ b/src/test/subscription/t/001_rep_changes.pl
@@ -11,6 +11,7 @@ use Test::More;
 # Initialize publisher node
 my $node_publisher = PostgreSQL::Test::Cluster->new('publisher');
 $node_publisher->init(allows_streaming => 'logical');
+$node_publisher->append_conf('postgresql.conf', "stats_flush_interval = '1s'");
 $node_publisher->start;
 
 # Create subscriber node
-- 
2.34.1


--C2xzVbxFmVrP7k6O
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v7-0005-Change-RELATION-and-DATABASE-stats-to-anytime-flu.patch"



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

* [PATCH v8 4/5] Remove useless calls to flush some stats
@ 2026-01-06 11:06  Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-06 11:06 UTC (permalink / raw)

Now that some stats can be flushed outside of transaction boundaries, remove
useless calls to report/flush some stats. Those calls were in place because
before commit <XXXX> stats were flushed only at transaction boundaries.

Note that:

- it reverts 039549d70f6 (it just keeps its tests)
- it can't be done for checkpointer and bgworker for example because they don't
have a flush callback to call
- it can't be done for auxiliary process (walsummarizer for example) because they
currently do not register the new timeout handler
---
 src/backend/replication/walreceiver.c        | 10 ------
 src/backend/replication/walsender.c          | 36 ++------------------
 src/backend/utils/activity/pgstat_relation.c | 13 -------
 src/test/recovery/t/001_stream_rep.pl        |  1 +
 src/test/subscription/t/001_rep_changes.pl   |  1 +
 5 files changed, 4 insertions(+), 57 deletions(-)
  69.4% src/backend/replication/
  23.4% src/backend/utils/activity/
   3.5% src/test/recovery/t/
   3.6% src/test/subscription/t/

diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index 11b7c114d3b..953ba97ed00 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -571,16 +571,6 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 					 */
 					bool		requestReply = false;
 
-					/*
-					 * Report pending statistics to the cumulative stats
-					 * system.  This location is useful for the report as it
-					 * is not within a tight loop in the WAL receiver, to
-					 * avoid bloating pgstats with requests, while also making
-					 * sure that the reports happen each time a status update
-					 * is sent.
-					 */
-					pgstat_report_wal(false);
-
 					/*
 					 * Check if time since last receive from primary has
 					 * reached the configured limit.
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index a7214d0dc6f..9a136e35b48 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -94,14 +94,10 @@
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 #include "utils/pg_lsn.h"
-#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
 #include "utils/timeout.h"
 #include "utils/timestamp.h"
 
-/* Minimum interval used by walsender for stats flushes, in ms */
-#define WALSENDER_STATS_FLUSH_INTERVAL         1000
-
 /*
  * Maximum data payload in a WAL data message.  Must be >= XLOG_BLCKSZ.
  *
@@ -1846,7 +1842,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	int			wakeEvents;
 	uint32		wait_event = 0;
 	static XLogRecPtr RecentFlushPtr = InvalidXLogRecPtr;
-	TimestampTz last_flush = 0;
 
 	/*
 	 * Fast path to avoid acquiring the spinlock in case we already know we
@@ -1867,7 +1862,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	{
 		bool		wait_for_standby_at_stop = false;
 		long		sleeptime;
-		TimestampTz now;
 
 		/* Clear any already-pending wakeups */
 		ResetLatch(MyLatch);
@@ -1973,8 +1967,7 @@ WalSndWaitForWal(XLogRecPtr loc)
 		 * new WAL to be generated.  (But if we have nothing to send, we don't
 		 * want to wake on socket-writable.)
 		 */
-		now = GetCurrentTimestamp();
-		sleeptime = WalSndComputeSleeptime(now);
+		sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 		wakeEvents = WL_SOCKET_READABLE;
 
@@ -1983,15 +1976,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 
 		Assert(wait_event != 0);
 
-		/* Report IO statistics, if needed */
-		if (TimestampDifferenceExceeds(last_flush, now,
-									   WALSENDER_STATS_FLUSH_INTERVAL))
-		{
-			pgstat_flush_io(false, true);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
-			last_flush = now;
-		}
-
 		WalSndWait(wakeEvents, sleeptime, wait_event);
 	}
 
@@ -2894,8 +2878,6 @@ WalSndCheckTimeOut(void)
 static void
 WalSndLoop(WalSndSendDataCallback send_data)
 {
-	TimestampTz last_flush = 0;
-
 	/*
 	 * Initialize the last reply timestamp. That enables timeout processing
 	 * from hereon.
@@ -2985,9 +2967,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		 * WalSndWaitForWal() handle any other blocking; idle receivers need
 		 * its additional actions.  For physical replication, also block if
 		 * caught up; its send_data does not block.
-		 *
-		 * The IO statistics are reported in WalSndWaitForWal() for the
-		 * logical WAL senders.
 		 */
 		if ((WalSndCaughtUp && send_data != XLogSendLogical &&
 			 !streamingDoneSending) ||
@@ -2995,7 +2974,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		{
 			long		sleeptime;
 			int			wakeEvents;
-			TimestampTz now;
 
 			if (!streamingDoneReceiving)
 				wakeEvents = WL_SOCKET_READABLE;
@@ -3006,21 +2984,11 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			 * Use fresh timestamp, not last_processing, to reduce the chance
 			 * of reaching wal_sender_timeout before sending a keepalive.
 			 */
-			now = GetCurrentTimestamp();
-			sleeptime = WalSndComputeSleeptime(now);
+			sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 			if (pq_is_send_pending())
 				wakeEvents |= WL_SOCKET_WRITEABLE;
 
-			/* Report IO statistics, if needed */
-			if (TimestampDifferenceExceeds(last_flush, now,
-										   WALSENDER_STATS_FLUSH_INTERVAL))
-			{
-				pgstat_flush_io(false, true);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
-				last_flush = now;
-			}
-
 			/* Sleep until something happens or we time out */
 			WalSndWait(wakeEvents, sleeptime, WAIT_EVENT_WAL_SENDER_MAIN);
 		}
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 04d21483d93..ae2952cae89 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -260,15 +260,6 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/*
-	 * Flush IO statistics now. pgstat_report_stat() will flush IO stats,
-	 * however this will not be called until after an entire autovacuum cycle
-	 * is done -- which will likely vacuum many relations -- or until the
-	 * VACUUM command has processed all tables and committed.
-	 */
-	pgstat_flush_io(false, true);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -360,10 +351,6 @@ pgstat_report_analyze(Relation rel,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/* see pgstat_report_vacuum() */
-	pgstat_flush_io(false, true);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
diff --git a/src/test/recovery/t/001_stream_rep.pl b/src/test/recovery/t/001_stream_rep.pl
index e9ac67813c7..cfa095ff0a8 100644
--- a/src/test/recovery/t/001_stream_rep.pl
+++ b/src/test/recovery/t/001_stream_rep.pl
@@ -15,6 +15,7 @@ my $node_primary = PostgreSQL::Test::Cluster->new('primary');
 $node_primary->init(
 	allows_streaming => 1,
 	auth_extra => [ '--create-role' => 'repl_role' ]);
+$node_primary->append_conf('postgresql.conf', "stats_flush_interval = '1s'");
 $node_primary->start;
 my $backup_name = 'my_backup';
 
diff --git a/src/test/subscription/t/001_rep_changes.pl b/src/test/subscription/t/001_rep_changes.pl
index 7d41715ed81..29bae5e1121 100644
--- a/src/test/subscription/t/001_rep_changes.pl
+++ b/src/test/subscription/t/001_rep_changes.pl
@@ -11,6 +11,7 @@ use Test::More;
 # Initialize publisher node
 my $node_publisher = PostgreSQL::Test::Cluster->new('publisher');
 $node_publisher->init(allows_streaming => 'logical');
+$node_publisher->append_conf('postgresql.conf', "stats_flush_interval = '1s'");
 $node_publisher->start;
 
 # Create subscriber node
-- 
2.34.1


--OI5irqZsxWxBW9nT
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v8-0005-Change-RELATION-and-DATABASE-stats-to-anytime-flu.patch"



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

* [PATCH v9 4/5] Remove useless calls to flush some stats
@ 2026-01-06 11:06  Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-06 11:06 UTC (permalink / raw)

Now that some stats can be flushed outside of transaction boundaries, remove
useless calls to report/flush some stats. Those calls were in place because
before commit <XXXX> stats were flushed only at transaction boundaries.

Note that:

- it reverts 039549d70f6 (it just keeps its tests)
- it can't be done for checkpointer and bgworker for example because they don't
have a flush callback to call
- it can't be done for auxiliary process (walsummarizer for example) because they
currently do not register the new timeout handler
---
 src/backend/replication/walreceiver.c        | 10 ------
 src/backend/replication/walsender.c          | 36 ++------------------
 src/backend/utils/activity/pgstat_relation.c | 13 -------
 src/test/recovery/t/001_stream_rep.pl        |  1 +
 src/test/subscription/t/001_rep_changes.pl   |  1 +
 5 files changed, 4 insertions(+), 57 deletions(-)
  69.4% src/backend/replication/
  23.4% src/backend/utils/activity/
   3.5% src/test/recovery/t/
   3.6% src/test/subscription/t/

diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index 11b7c114d3b..953ba97ed00 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -571,16 +571,6 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 					 */
 					bool		requestReply = false;
 
-					/*
-					 * Report pending statistics to the cumulative stats
-					 * system.  This location is useful for the report as it
-					 * is not within a tight loop in the WAL receiver, to
-					 * avoid bloating pgstats with requests, while also making
-					 * sure that the reports happen each time a status update
-					 * is sent.
-					 */
-					pgstat_report_wal(false);
-
 					/*
 					 * Check if time since last receive from primary has
 					 * reached the configured limit.
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index a7214d0dc6f..9a136e35b48 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -94,14 +94,10 @@
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 #include "utils/pg_lsn.h"
-#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
 #include "utils/timeout.h"
 #include "utils/timestamp.h"
 
-/* Minimum interval used by walsender for stats flushes, in ms */
-#define WALSENDER_STATS_FLUSH_INTERVAL         1000
-
 /*
  * Maximum data payload in a WAL data message.  Must be >= XLOG_BLCKSZ.
  *
@@ -1846,7 +1842,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	int			wakeEvents;
 	uint32		wait_event = 0;
 	static XLogRecPtr RecentFlushPtr = InvalidXLogRecPtr;
-	TimestampTz last_flush = 0;
 
 	/*
 	 * Fast path to avoid acquiring the spinlock in case we already know we
@@ -1867,7 +1862,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	{
 		bool		wait_for_standby_at_stop = false;
 		long		sleeptime;
-		TimestampTz now;
 
 		/* Clear any already-pending wakeups */
 		ResetLatch(MyLatch);
@@ -1973,8 +1967,7 @@ WalSndWaitForWal(XLogRecPtr loc)
 		 * new WAL to be generated.  (But if we have nothing to send, we don't
 		 * want to wake on socket-writable.)
 		 */
-		now = GetCurrentTimestamp();
-		sleeptime = WalSndComputeSleeptime(now);
+		sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 		wakeEvents = WL_SOCKET_READABLE;
 
@@ -1983,15 +1976,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 
 		Assert(wait_event != 0);
 
-		/* Report IO statistics, if needed */
-		if (TimestampDifferenceExceeds(last_flush, now,
-									   WALSENDER_STATS_FLUSH_INTERVAL))
-		{
-			pgstat_flush_io(false, true);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
-			last_flush = now;
-		}
-
 		WalSndWait(wakeEvents, sleeptime, wait_event);
 	}
 
@@ -2894,8 +2878,6 @@ WalSndCheckTimeOut(void)
 static void
 WalSndLoop(WalSndSendDataCallback send_data)
 {
-	TimestampTz last_flush = 0;
-
 	/*
 	 * Initialize the last reply timestamp. That enables timeout processing
 	 * from hereon.
@@ -2985,9 +2967,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		 * WalSndWaitForWal() handle any other blocking; idle receivers need
 		 * its additional actions.  For physical replication, also block if
 		 * caught up; its send_data does not block.
-		 *
-		 * The IO statistics are reported in WalSndWaitForWal() for the
-		 * logical WAL senders.
 		 */
 		if ((WalSndCaughtUp && send_data != XLogSendLogical &&
 			 !streamingDoneSending) ||
@@ -2995,7 +2974,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		{
 			long		sleeptime;
 			int			wakeEvents;
-			TimestampTz now;
 
 			if (!streamingDoneReceiving)
 				wakeEvents = WL_SOCKET_READABLE;
@@ -3006,21 +2984,11 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			 * Use fresh timestamp, not last_processing, to reduce the chance
 			 * of reaching wal_sender_timeout before sending a keepalive.
 			 */
-			now = GetCurrentTimestamp();
-			sleeptime = WalSndComputeSleeptime(now);
+			sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 			if (pq_is_send_pending())
 				wakeEvents |= WL_SOCKET_WRITEABLE;
 
-			/* Report IO statistics, if needed */
-			if (TimestampDifferenceExceeds(last_flush, now,
-										   WALSENDER_STATS_FLUSH_INTERVAL))
-			{
-				pgstat_flush_io(false, true);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
-				last_flush = now;
-			}
-
 			/* Sleep until something happens or we time out */
 			WalSndWait(wakeEvents, sleeptime, WAIT_EVENT_WAL_SENDER_MAIN);
 		}
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 04d21483d93..ae2952cae89 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -260,15 +260,6 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/*
-	 * Flush IO statistics now. pgstat_report_stat() will flush IO stats,
-	 * however this will not be called until after an entire autovacuum cycle
-	 * is done -- which will likely vacuum many relations -- or until the
-	 * VACUUM command has processed all tables and committed.
-	 */
-	pgstat_flush_io(false, true);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -360,10 +351,6 @@ pgstat_report_analyze(Relation rel,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/* see pgstat_report_vacuum() */
-	pgstat_flush_io(false, true);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
diff --git a/src/test/recovery/t/001_stream_rep.pl b/src/test/recovery/t/001_stream_rep.pl
index e9ac67813c7..cfa095ff0a8 100644
--- a/src/test/recovery/t/001_stream_rep.pl
+++ b/src/test/recovery/t/001_stream_rep.pl
@@ -15,6 +15,7 @@ my $node_primary = PostgreSQL::Test::Cluster->new('primary');
 $node_primary->init(
 	allows_streaming => 1,
 	auth_extra => [ '--create-role' => 'repl_role' ]);
+$node_primary->append_conf('postgresql.conf', "stats_flush_interval = '1s'");
 $node_primary->start;
 my $backup_name = 'my_backup';
 
diff --git a/src/test/subscription/t/001_rep_changes.pl b/src/test/subscription/t/001_rep_changes.pl
index 7d41715ed81..29bae5e1121 100644
--- a/src/test/subscription/t/001_rep_changes.pl
+++ b/src/test/subscription/t/001_rep_changes.pl
@@ -11,6 +11,7 @@ use Test::More;
 # Initialize publisher node
 my $node_publisher = PostgreSQL::Test::Cluster->new('publisher');
 $node_publisher->init(allows_streaming => 'logical');
+$node_publisher->append_conf('postgresql.conf', "stats_flush_interval = '1s'");
 $node_publisher->start;
 
 # Create subscriber node
-- 
2.34.1


--aq/6bi8L6WORnI+9
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v9-0005-Change-RELATION-and-DATABASE-stats-to-anytime-flu.patch"



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

* [PATCH v10 4/5] Remove useless calls to flush some stats
@ 2026-01-06 11:06  Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-06 11:06 UTC (permalink / raw)

Now that some stats can be flushed outside of transaction boundaries, remove
useless calls to report/flush some stats. Those calls were in place because
before commit <XXXX> stats were flushed only at transaction boundaries.

Note that:

- it reverts 039549d70f6 (it just keeps its tests)
- it can't be done for checkpointer and bgworker for example because they don't
have a flush callback to call
- it can't be done for auxiliary process (walsummarizer for example) because they
currently do not register the new timeout handler
---
 src/backend/replication/walreceiver.c        | 10 ------
 src/backend/replication/walsender.c          | 36 ++------------------
 src/backend/utils/activity/pgstat_relation.c | 13 -------
 src/test/recovery/t/001_stream_rep.pl        |  1 +
 src/test/subscription/t/001_rep_changes.pl   |  1 +
 5 files changed, 4 insertions(+), 57 deletions(-)
  69.4% src/backend/replication/
  23.4% src/backend/utils/activity/
   3.5% src/test/recovery/t/
   3.6% src/test/subscription/t/

diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index aecc7a127e6..edf5ac65660 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -571,16 +571,6 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 					 */
 					bool		requestReply = false;
 
-					/*
-					 * Report pending statistics to the cumulative stats
-					 * system.  This location is useful for the report as it
-					 * is not within a tight loop in the WAL receiver, to
-					 * avoid bloating pgstats with requests, while also making
-					 * sure that the reports happen each time a status update
-					 * is sent.
-					 */
-					pgstat_report_wal(false);
-
 					/*
 					 * Check if time since last receive from primary has
 					 * reached the configured limit.
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index a7214d0dc6f..9a136e35b48 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -94,14 +94,10 @@
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 #include "utils/pg_lsn.h"
-#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
 #include "utils/timeout.h"
 #include "utils/timestamp.h"
 
-/* Minimum interval used by walsender for stats flushes, in ms */
-#define WALSENDER_STATS_FLUSH_INTERVAL         1000
-
 /*
  * Maximum data payload in a WAL data message.  Must be >= XLOG_BLCKSZ.
  *
@@ -1846,7 +1842,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	int			wakeEvents;
 	uint32		wait_event = 0;
 	static XLogRecPtr RecentFlushPtr = InvalidXLogRecPtr;
-	TimestampTz last_flush = 0;
 
 	/*
 	 * Fast path to avoid acquiring the spinlock in case we already know we
@@ -1867,7 +1862,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	{
 		bool		wait_for_standby_at_stop = false;
 		long		sleeptime;
-		TimestampTz now;
 
 		/* Clear any already-pending wakeups */
 		ResetLatch(MyLatch);
@@ -1973,8 +1967,7 @@ WalSndWaitForWal(XLogRecPtr loc)
 		 * new WAL to be generated.  (But if we have nothing to send, we don't
 		 * want to wake on socket-writable.)
 		 */
-		now = GetCurrentTimestamp();
-		sleeptime = WalSndComputeSleeptime(now);
+		sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 		wakeEvents = WL_SOCKET_READABLE;
 
@@ -1983,15 +1976,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 
 		Assert(wait_event != 0);
 
-		/* Report IO statistics, if needed */
-		if (TimestampDifferenceExceeds(last_flush, now,
-									   WALSENDER_STATS_FLUSH_INTERVAL))
-		{
-			pgstat_flush_io(false, true);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
-			last_flush = now;
-		}
-
 		WalSndWait(wakeEvents, sleeptime, wait_event);
 	}
 
@@ -2894,8 +2878,6 @@ WalSndCheckTimeOut(void)
 static void
 WalSndLoop(WalSndSendDataCallback send_data)
 {
-	TimestampTz last_flush = 0;
-
 	/*
 	 * Initialize the last reply timestamp. That enables timeout processing
 	 * from hereon.
@@ -2985,9 +2967,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		 * WalSndWaitForWal() handle any other blocking; idle receivers need
 		 * its additional actions.  For physical replication, also block if
 		 * caught up; its send_data does not block.
-		 *
-		 * The IO statistics are reported in WalSndWaitForWal() for the
-		 * logical WAL senders.
 		 */
 		if ((WalSndCaughtUp && send_data != XLogSendLogical &&
 			 !streamingDoneSending) ||
@@ -2995,7 +2974,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		{
 			long		sleeptime;
 			int			wakeEvents;
-			TimestampTz now;
 
 			if (!streamingDoneReceiving)
 				wakeEvents = WL_SOCKET_READABLE;
@@ -3006,21 +2984,11 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			 * Use fresh timestamp, not last_processing, to reduce the chance
 			 * of reaching wal_sender_timeout before sending a keepalive.
 			 */
-			now = GetCurrentTimestamp();
-			sleeptime = WalSndComputeSleeptime(now);
+			sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 			if (pq_is_send_pending())
 				wakeEvents |= WL_SOCKET_WRITEABLE;
 
-			/* Report IO statistics, if needed */
-			if (TimestampDifferenceExceeds(last_flush, now,
-										   WALSENDER_STATS_FLUSH_INTERVAL))
-			{
-				pgstat_flush_io(false, true);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
-				last_flush = now;
-			}
-
 			/* Sleep until something happens or we time out */
 			WalSndWait(wakeEvents, sleeptime, WAIT_EVENT_WAL_SENDER_MAIN);
 		}
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 04d21483d93..ae2952cae89 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -260,15 +260,6 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/*
-	 * Flush IO statistics now. pgstat_report_stat() will flush IO stats,
-	 * however this will not be called until after an entire autovacuum cycle
-	 * is done -- which will likely vacuum many relations -- or until the
-	 * VACUUM command has processed all tables and committed.
-	 */
-	pgstat_flush_io(false, true);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -360,10 +351,6 @@ pgstat_report_analyze(Relation rel,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/* see pgstat_report_vacuum() */
-	pgstat_flush_io(false, true);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
diff --git a/src/test/recovery/t/001_stream_rep.pl b/src/test/recovery/t/001_stream_rep.pl
index e9ac67813c7..cfa095ff0a8 100644
--- a/src/test/recovery/t/001_stream_rep.pl
+++ b/src/test/recovery/t/001_stream_rep.pl
@@ -15,6 +15,7 @@ my $node_primary = PostgreSQL::Test::Cluster->new('primary');
 $node_primary->init(
 	allows_streaming => 1,
 	auth_extra => [ '--create-role' => 'repl_role' ]);
+$node_primary->append_conf('postgresql.conf', "stats_flush_interval = '1s'");
 $node_primary->start;
 my $backup_name = 'my_backup';
 
diff --git a/src/test/subscription/t/001_rep_changes.pl b/src/test/subscription/t/001_rep_changes.pl
index 7d41715ed81..29bae5e1121 100644
--- a/src/test/subscription/t/001_rep_changes.pl
+++ b/src/test/subscription/t/001_rep_changes.pl
@@ -11,6 +11,7 @@ use Test::More;
 # Initialize publisher node
 my $node_publisher = PostgreSQL::Test::Cluster->new('publisher');
 $node_publisher->init(allows_streaming => 'logical');
+$node_publisher->append_conf('postgresql.conf', "stats_flush_interval = '1s'");
 $node_publisher->start;
 
 # Create subscriber node
-- 
2.34.1


--NVvBxFuyV/R+1/8/
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v10-0005-Change-RELATION-and-DATABASE-stats-to-anytime-fl.patch"



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

* [PATCH v11 4/5] Remove useless calls to flush some stats
@ 2026-01-06 11:06  Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-06 11:06 UTC (permalink / raw)

Now that some stats can be flushed outside of transaction boundaries, remove
useless calls to report/flush some stats. Those calls were in place because
before commit <XXXX> stats were flushed only at transaction boundaries.

Note that:

- it reverts 039549d70f6 (it just keeps its tests)
- it can't be done for checkpointer and bgworker for example because they don't
have a flush callback to call
- it can't be done for auxiliary process (walsummarizer for example) because they
currently do not register the new timeout handler
---
 src/backend/replication/walreceiver.c        | 10 ------
 src/backend/replication/walsender.c          | 36 ++------------------
 src/backend/utils/activity/pgstat_relation.c | 13 -------
 src/test/recovery/t/001_stream_rep.pl        |  1 +
 src/test/subscription/t/001_rep_changes.pl   |  1 +
 5 files changed, 4 insertions(+), 57 deletions(-)
  69.4% src/backend/replication/
  23.4% src/backend/utils/activity/
   3.5% src/test/recovery/t/
   3.6% src/test/subscription/t/

diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index aecc7a127e6..edf5ac65660 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -571,16 +571,6 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 					 */
 					bool		requestReply = false;
 
-					/*
-					 * Report pending statistics to the cumulative stats
-					 * system.  This location is useful for the report as it
-					 * is not within a tight loop in the WAL receiver, to
-					 * avoid bloating pgstats with requests, while also making
-					 * sure that the reports happen each time a status update
-					 * is sent.
-					 */
-					pgstat_report_wal(false);
-
 					/*
 					 * Check if time since last receive from primary has
 					 * reached the configured limit.
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index a7214d0dc6f..9a136e35b48 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -94,14 +94,10 @@
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 #include "utils/pg_lsn.h"
-#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
 #include "utils/timeout.h"
 #include "utils/timestamp.h"
 
-/* Minimum interval used by walsender for stats flushes, in ms */
-#define WALSENDER_STATS_FLUSH_INTERVAL         1000
-
 /*
  * Maximum data payload in a WAL data message.  Must be >= XLOG_BLCKSZ.
  *
@@ -1846,7 +1842,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	int			wakeEvents;
 	uint32		wait_event = 0;
 	static XLogRecPtr RecentFlushPtr = InvalidXLogRecPtr;
-	TimestampTz last_flush = 0;
 
 	/*
 	 * Fast path to avoid acquiring the spinlock in case we already know we
@@ -1867,7 +1862,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	{
 		bool		wait_for_standby_at_stop = false;
 		long		sleeptime;
-		TimestampTz now;
 
 		/* Clear any already-pending wakeups */
 		ResetLatch(MyLatch);
@@ -1973,8 +1967,7 @@ WalSndWaitForWal(XLogRecPtr loc)
 		 * new WAL to be generated.  (But if we have nothing to send, we don't
 		 * want to wake on socket-writable.)
 		 */
-		now = GetCurrentTimestamp();
-		sleeptime = WalSndComputeSleeptime(now);
+		sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 		wakeEvents = WL_SOCKET_READABLE;
 
@@ -1983,15 +1976,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 
 		Assert(wait_event != 0);
 
-		/* Report IO statistics, if needed */
-		if (TimestampDifferenceExceeds(last_flush, now,
-									   WALSENDER_STATS_FLUSH_INTERVAL))
-		{
-			pgstat_flush_io(false, true);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
-			last_flush = now;
-		}
-
 		WalSndWait(wakeEvents, sleeptime, wait_event);
 	}
 
@@ -2894,8 +2878,6 @@ WalSndCheckTimeOut(void)
 static void
 WalSndLoop(WalSndSendDataCallback send_data)
 {
-	TimestampTz last_flush = 0;
-
 	/*
 	 * Initialize the last reply timestamp. That enables timeout processing
 	 * from hereon.
@@ -2985,9 +2967,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		 * WalSndWaitForWal() handle any other blocking; idle receivers need
 		 * its additional actions.  For physical replication, also block if
 		 * caught up; its send_data does not block.
-		 *
-		 * The IO statistics are reported in WalSndWaitForWal() for the
-		 * logical WAL senders.
 		 */
 		if ((WalSndCaughtUp && send_data != XLogSendLogical &&
 			 !streamingDoneSending) ||
@@ -2995,7 +2974,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		{
 			long		sleeptime;
 			int			wakeEvents;
-			TimestampTz now;
 
 			if (!streamingDoneReceiving)
 				wakeEvents = WL_SOCKET_READABLE;
@@ -3006,21 +2984,11 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			 * Use fresh timestamp, not last_processing, to reduce the chance
 			 * of reaching wal_sender_timeout before sending a keepalive.
 			 */
-			now = GetCurrentTimestamp();
-			sleeptime = WalSndComputeSleeptime(now);
+			sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 			if (pq_is_send_pending())
 				wakeEvents |= WL_SOCKET_WRITEABLE;
 
-			/* Report IO statistics, if needed */
-			if (TimestampDifferenceExceeds(last_flush, now,
-										   WALSENDER_STATS_FLUSH_INTERVAL))
-			{
-				pgstat_flush_io(false, true);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
-				last_flush = now;
-			}
-
 			/* Sleep until something happens or we time out */
 			WalSndWait(wakeEvents, sleeptime, WAIT_EVENT_WAL_SENDER_MAIN);
 		}
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 04d21483d93..ae2952cae89 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -260,15 +260,6 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/*
-	 * Flush IO statistics now. pgstat_report_stat() will flush IO stats,
-	 * however this will not be called until after an entire autovacuum cycle
-	 * is done -- which will likely vacuum many relations -- or until the
-	 * VACUUM command has processed all tables and committed.
-	 */
-	pgstat_flush_io(false, true);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
@@ -360,10 +351,6 @@ pgstat_report_analyze(Relation rel,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/* see pgstat_report_vacuum() */
-	pgstat_flush_io(false, true);
-	(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO, true);
 }
 
 /*
diff --git a/src/test/recovery/t/001_stream_rep.pl b/src/test/recovery/t/001_stream_rep.pl
index e9ac67813c7..cfa095ff0a8 100644
--- a/src/test/recovery/t/001_stream_rep.pl
+++ b/src/test/recovery/t/001_stream_rep.pl
@@ -15,6 +15,7 @@ my $node_primary = PostgreSQL::Test::Cluster->new('primary');
 $node_primary->init(
 	allows_streaming => 1,
 	auth_extra => [ '--create-role' => 'repl_role' ]);
+$node_primary->append_conf('postgresql.conf', "stats_flush_interval = '1s'");
 $node_primary->start;
 my $backup_name = 'my_backup';
 
diff --git a/src/test/subscription/t/001_rep_changes.pl b/src/test/subscription/t/001_rep_changes.pl
index 7d41715ed81..29bae5e1121 100644
--- a/src/test/subscription/t/001_rep_changes.pl
+++ b/src/test/subscription/t/001_rep_changes.pl
@@ -11,6 +11,7 @@ use Test::More;
 # Initialize publisher node
 my $node_publisher = PostgreSQL::Test::Cluster->new('publisher');
 $node_publisher->init(allows_streaming => 'logical');
+$node_publisher->append_conf('postgresql.conf', "stats_flush_interval = '1s'");
 $node_publisher->start;
 
 # Create subscriber node
-- 
2.34.1


--2MEBAGW8+kohXisi
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v11-0005-Change-RELATION-and-DATABASE-stats-to-anytime-fl.patch"



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

* [PATCH v1 2/3] Remove useless calls to flush some stats
@ 2026-01-06 11:06  Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-06 11:06 UTC (permalink / raw)

Now that some stats can be flushed outside of transaction boundaries, remove
useless calls to report/flush some stats. Those calls were in place because
before commit <XXXX> stats were flushed only at transaction boundaries.

Note that:

- it reverts 039549d70f6 (it just keeps its tests)
- it can't be done for checkpointer and bgworker for example because they don't
have a flush callback to call
- it can't be done for auxiliary process (walsummarizer for example) because they
currently do not register the new timeout handler
---
 src/backend/replication/walreceiver.c        | 10 ------
 src/backend/replication/walsender.c          | 36 ++------------------
 src/backend/utils/activity/pgstat_relation.c | 13 -------
 3 files changed, 2 insertions(+), 57 deletions(-)
  75.3% src/backend/replication/
  24.6% src/backend/utils/activity/

diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index a41453530a1..266379c780a 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -553,16 +553,6 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 					 */
 					bool		requestReply = false;
 
-					/*
-					 * Report pending statistics to the cumulative stats
-					 * system.  This location is useful for the report as it
-					 * is not within a tight loop in the WAL receiver, to
-					 * avoid bloating pgstats with requests, while also making
-					 * sure that the reports happen each time a status update
-					 * is sent.
-					 */
-					pgstat_report_wal(false);
-
 					/*
 					 * Check if time since last receive from primary has
 					 * reached the configured limit.
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 1ab09655a70..c33185bd337 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -94,14 +94,10 @@
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 #include "utils/pg_lsn.h"
-#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
 #include "utils/timeout.h"
 #include "utils/timestamp.h"
 
-/* Minimum interval used by walsender for stats flushes, in ms */
-#define WALSENDER_STATS_FLUSH_INTERVAL         1000
-
 /*
  * Maximum data payload in a WAL data message.  Must be >= XLOG_BLCKSZ.
  *
@@ -1826,7 +1822,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	int			wakeEvents;
 	uint32		wait_event = 0;
 	static XLogRecPtr RecentFlushPtr = InvalidXLogRecPtr;
-	TimestampTz last_flush = 0;
 
 	/*
 	 * Fast path to avoid acquiring the spinlock in case we already know we
@@ -1847,7 +1842,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	{
 		bool		wait_for_standby_at_stop = false;
 		long		sleeptime;
-		TimestampTz now;
 
 		/* Clear any already-pending wakeups */
 		ResetLatch(MyLatch);
@@ -1958,8 +1952,7 @@ WalSndWaitForWal(XLogRecPtr loc)
 		 * new WAL to be generated.  (But if we have nothing to send, we don't
 		 * want to wake on socket-writable.)
 		 */
-		now = GetCurrentTimestamp();
-		sleeptime = WalSndComputeSleeptime(now);
+		sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 		wakeEvents = WL_SOCKET_READABLE;
 
@@ -1968,15 +1961,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 
 		Assert(wait_event != 0);
 
-		/* Report IO statistics, if needed */
-		if (TimestampDifferenceExceeds(last_flush, now,
-									   WALSENDER_STATS_FLUSH_INTERVAL))
-		{
-			pgstat_flush_io(false);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
-			last_flush = now;
-		}
-
 		WalSndWait(wakeEvents, sleeptime, wait_event);
 	}
 
@@ -2879,8 +2863,6 @@ WalSndCheckTimeOut(void)
 static void
 WalSndLoop(WalSndSendDataCallback send_data)
 {
-	TimestampTz last_flush = 0;
-
 	/*
 	 * Initialize the last reply timestamp. That enables timeout processing
 	 * from hereon.
@@ -2975,9 +2957,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		 * WalSndWaitForWal() handle any other blocking; idle receivers need
 		 * its additional actions.  For physical replication, also block if
 		 * caught up; its send_data does not block.
-		 *
-		 * The IO statistics are reported in WalSndWaitForWal() for the
-		 * logical WAL senders.
 		 */
 		if ((WalSndCaughtUp && send_data != XLogSendLogical &&
 			 !streamingDoneSending) ||
@@ -2985,7 +2964,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		{
 			long		sleeptime;
 			int			wakeEvents;
-			TimestampTz now;
 
 			if (!streamingDoneReceiving)
 				wakeEvents = WL_SOCKET_READABLE;
@@ -2996,21 +2974,11 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			 * Use fresh timestamp, not last_processing, to reduce the chance
 			 * of reaching wal_sender_timeout before sending a keepalive.
 			 */
-			now = GetCurrentTimestamp();
-			sleeptime = WalSndComputeSleeptime(now);
+			sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 			if (pq_is_send_pending())
 				wakeEvents |= WL_SOCKET_WRITEABLE;
 
-			/* Report IO statistics, if needed */
-			if (TimestampDifferenceExceeds(last_flush, now,
-										   WALSENDER_STATS_FLUSH_INTERVAL))
-			{
-				pgstat_flush_io(false);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
-				last_flush = now;
-			}
-
 			/* Sleep until something happens or we time out */
 			WalSndWait(wakeEvents, sleeptime, WAIT_EVENT_WAL_SENDER_MAIN);
 		}
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..feae2ae5f44 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -260,15 +260,6 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/*
-	 * Flush IO statistics now. pgstat_report_stat() will flush IO stats,
-	 * however this will not be called until after an entire autovacuum cycle
-	 * 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);
 }
 
 /*
@@ -360,10 +351,6 @@ 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);
 }
 
 /*
-- 
2.34.1


--tjEWjIIwfNIHQLgt
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0003-Add-FLUSH_MIXED-support-and-implement-it-for-RELA.patch"



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

* [PATCH v2 2/3] Remove useless calls to flush some stats
@ 2026-01-06 11:06  Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-06 11:06 UTC (permalink / raw)

Now that some stats can be flushed outside of transaction boundaries, remove
useless calls to report/flush some stats. Those calls were in place because
before commit <XXXX> stats were flushed only at transaction boundaries.

Note that:

- it reverts 039549d70f6 (it just keeps its tests)
- it can't be done for checkpointer and bgworker for example because they don't
have a flush callback to call
- it can't be done for auxiliary process (walsummarizer for example) because they
currently do not register the new timeout handler
---
 src/backend/replication/walreceiver.c        | 10 ------
 src/backend/replication/walsender.c          | 36 ++------------------
 src/backend/utils/activity/pgstat_relation.c | 13 -------
 3 files changed, 2 insertions(+), 57 deletions(-)
  75.3% src/backend/replication/
  24.6% src/backend/utils/activity/

diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index a41453530a1..266379c780a 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -553,16 +553,6 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 					 */
 					bool		requestReply = false;
 
-					/*
-					 * Report pending statistics to the cumulative stats
-					 * system.  This location is useful for the report as it
-					 * is not within a tight loop in the WAL receiver, to
-					 * avoid bloating pgstats with requests, while also making
-					 * sure that the reports happen each time a status update
-					 * is sent.
-					 */
-					pgstat_report_wal(false);
-
 					/*
 					 * Check if time since last receive from primary has
 					 * reached the configured limit.
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 1ab09655a70..c33185bd337 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -94,14 +94,10 @@
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 #include "utils/pg_lsn.h"
-#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
 #include "utils/timeout.h"
 #include "utils/timestamp.h"
 
-/* Minimum interval used by walsender for stats flushes, in ms */
-#define WALSENDER_STATS_FLUSH_INTERVAL         1000
-
 /*
  * Maximum data payload in a WAL data message.  Must be >= XLOG_BLCKSZ.
  *
@@ -1826,7 +1822,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	int			wakeEvents;
 	uint32		wait_event = 0;
 	static XLogRecPtr RecentFlushPtr = InvalidXLogRecPtr;
-	TimestampTz last_flush = 0;
 
 	/*
 	 * Fast path to avoid acquiring the spinlock in case we already know we
@@ -1847,7 +1842,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	{
 		bool		wait_for_standby_at_stop = false;
 		long		sleeptime;
-		TimestampTz now;
 
 		/* Clear any already-pending wakeups */
 		ResetLatch(MyLatch);
@@ -1958,8 +1952,7 @@ WalSndWaitForWal(XLogRecPtr loc)
 		 * new WAL to be generated.  (But if we have nothing to send, we don't
 		 * want to wake on socket-writable.)
 		 */
-		now = GetCurrentTimestamp();
-		sleeptime = WalSndComputeSleeptime(now);
+		sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 		wakeEvents = WL_SOCKET_READABLE;
 
@@ -1968,15 +1961,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 
 		Assert(wait_event != 0);
 
-		/* Report IO statistics, if needed */
-		if (TimestampDifferenceExceeds(last_flush, now,
-									   WALSENDER_STATS_FLUSH_INTERVAL))
-		{
-			pgstat_flush_io(false);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
-			last_flush = now;
-		}
-
 		WalSndWait(wakeEvents, sleeptime, wait_event);
 	}
 
@@ -2879,8 +2863,6 @@ WalSndCheckTimeOut(void)
 static void
 WalSndLoop(WalSndSendDataCallback send_data)
 {
-	TimestampTz last_flush = 0;
-
 	/*
 	 * Initialize the last reply timestamp. That enables timeout processing
 	 * from hereon.
@@ -2975,9 +2957,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		 * WalSndWaitForWal() handle any other blocking; idle receivers need
 		 * its additional actions.  For physical replication, also block if
 		 * caught up; its send_data does not block.
-		 *
-		 * The IO statistics are reported in WalSndWaitForWal() for the
-		 * logical WAL senders.
 		 */
 		if ((WalSndCaughtUp && send_data != XLogSendLogical &&
 			 !streamingDoneSending) ||
@@ -2985,7 +2964,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		{
 			long		sleeptime;
 			int			wakeEvents;
-			TimestampTz now;
 
 			if (!streamingDoneReceiving)
 				wakeEvents = WL_SOCKET_READABLE;
@@ -2996,21 +2974,11 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			 * Use fresh timestamp, not last_processing, to reduce the chance
 			 * of reaching wal_sender_timeout before sending a keepalive.
 			 */
-			now = GetCurrentTimestamp();
-			sleeptime = WalSndComputeSleeptime(now);
+			sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 			if (pq_is_send_pending())
 				wakeEvents |= WL_SOCKET_WRITEABLE;
 
-			/* Report IO statistics, if needed */
-			if (TimestampDifferenceExceeds(last_flush, now,
-										   WALSENDER_STATS_FLUSH_INTERVAL))
-			{
-				pgstat_flush_io(false);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
-				last_flush = now;
-			}
-
 			/* Sleep until something happens or we time out */
 			WalSndWait(wakeEvents, sleeptime, WAIT_EVENT_WAL_SENDER_MAIN);
 		}
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..feae2ae5f44 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -260,15 +260,6 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/*
-	 * Flush IO statistics now. pgstat_report_stat() will flush IO stats,
-	 * however this will not be called until after an entire autovacuum cycle
-	 * 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);
 }
 
 /*
@@ -360,10 +351,6 @@ 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);
 }
 
 /*
-- 
2.34.1


--OFsrIl+bjhifp5hk
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0003-Add-FLUSH_MIXED-support-and-implement-it-for-RELA.patch"



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

* [PATCH v3 2/3] Remove useless calls to flush some stats
@ 2026-01-06 11:06  Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-06 11:06 UTC (permalink / raw)

Now that some stats can be flushed outside of transaction boundaries, remove
useless calls to report/flush some stats. Those calls were in place because
before commit <XXXX> stats were flushed only at transaction boundaries.

Note that:

- it reverts 039549d70f6 (it just keeps its tests)
- it can't be done for checkpointer and bgworker for example because they don't
have a flush callback to call
- it can't be done for auxiliary process (walsummarizer for example) because they
currently do not register the new timeout handler
---
 src/backend/replication/walreceiver.c        | 10 ------
 src/backend/replication/walsender.c          | 36 ++------------------
 src/backend/utils/activity/pgstat_relation.c | 13 -------
 3 files changed, 2 insertions(+), 57 deletions(-)
  75.3% src/backend/replication/
  24.6% src/backend/utils/activity/

diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index a41453530a1..266379c780a 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -553,16 +553,6 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 					 */
 					bool		requestReply = false;
 
-					/*
-					 * Report pending statistics to the cumulative stats
-					 * system.  This location is useful for the report as it
-					 * is not within a tight loop in the WAL receiver, to
-					 * avoid bloating pgstats with requests, while also making
-					 * sure that the reports happen each time a status update
-					 * is sent.
-					 */
-					pgstat_report_wal(false);
-
 					/*
 					 * Check if time since last receive from primary has
 					 * reached the configured limit.
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 1ab09655a70..c33185bd337 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -94,14 +94,10 @@
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 #include "utils/pg_lsn.h"
-#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
 #include "utils/timeout.h"
 #include "utils/timestamp.h"
 
-/* Minimum interval used by walsender for stats flushes, in ms */
-#define WALSENDER_STATS_FLUSH_INTERVAL         1000
-
 /*
  * Maximum data payload in a WAL data message.  Must be >= XLOG_BLCKSZ.
  *
@@ -1826,7 +1822,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	int			wakeEvents;
 	uint32		wait_event = 0;
 	static XLogRecPtr RecentFlushPtr = InvalidXLogRecPtr;
-	TimestampTz last_flush = 0;
 
 	/*
 	 * Fast path to avoid acquiring the spinlock in case we already know we
@@ -1847,7 +1842,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	{
 		bool		wait_for_standby_at_stop = false;
 		long		sleeptime;
-		TimestampTz now;
 
 		/* Clear any already-pending wakeups */
 		ResetLatch(MyLatch);
@@ -1958,8 +1952,7 @@ WalSndWaitForWal(XLogRecPtr loc)
 		 * new WAL to be generated.  (But if we have nothing to send, we don't
 		 * want to wake on socket-writable.)
 		 */
-		now = GetCurrentTimestamp();
-		sleeptime = WalSndComputeSleeptime(now);
+		sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 		wakeEvents = WL_SOCKET_READABLE;
 
@@ -1968,15 +1961,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 
 		Assert(wait_event != 0);
 
-		/* Report IO statistics, if needed */
-		if (TimestampDifferenceExceeds(last_flush, now,
-									   WALSENDER_STATS_FLUSH_INTERVAL))
-		{
-			pgstat_flush_io(false);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
-			last_flush = now;
-		}
-
 		WalSndWait(wakeEvents, sleeptime, wait_event);
 	}
 
@@ -2879,8 +2863,6 @@ WalSndCheckTimeOut(void)
 static void
 WalSndLoop(WalSndSendDataCallback send_data)
 {
-	TimestampTz last_flush = 0;
-
 	/*
 	 * Initialize the last reply timestamp. That enables timeout processing
 	 * from hereon.
@@ -2975,9 +2957,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		 * WalSndWaitForWal() handle any other blocking; idle receivers need
 		 * its additional actions.  For physical replication, also block if
 		 * caught up; its send_data does not block.
-		 *
-		 * The IO statistics are reported in WalSndWaitForWal() for the
-		 * logical WAL senders.
 		 */
 		if ((WalSndCaughtUp && send_data != XLogSendLogical &&
 			 !streamingDoneSending) ||
@@ -2985,7 +2964,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		{
 			long		sleeptime;
 			int			wakeEvents;
-			TimestampTz now;
 
 			if (!streamingDoneReceiving)
 				wakeEvents = WL_SOCKET_READABLE;
@@ -2996,21 +2974,11 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			 * Use fresh timestamp, not last_processing, to reduce the chance
 			 * of reaching wal_sender_timeout before sending a keepalive.
 			 */
-			now = GetCurrentTimestamp();
-			sleeptime = WalSndComputeSleeptime(now);
+			sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 			if (pq_is_send_pending())
 				wakeEvents |= WL_SOCKET_WRITEABLE;
 
-			/* Report IO statistics, if needed */
-			if (TimestampDifferenceExceeds(last_flush, now,
-										   WALSENDER_STATS_FLUSH_INTERVAL))
-			{
-				pgstat_flush_io(false);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
-				last_flush = now;
-			}
-
 			/* Sleep until something happens or we time out */
 			WalSndWait(wakeEvents, sleeptime, WAIT_EVENT_WAL_SENDER_MAIN);
 		}
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..feae2ae5f44 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -260,15 +260,6 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/*
-	 * Flush IO statistics now. pgstat_report_stat() will flush IO stats,
-	 * however this will not be called until after an entire autovacuum cycle
-	 * 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);
 }
 
 /*
@@ -360,10 +351,6 @@ 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);
 }
 
 /*
-- 
2.34.1


--lCc1MWfC7i2uqs8g
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v3-0003-Add-FLUSH_MIXED-support-and-implement-it-for-RELA.patch"



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

* [PATCH v4 3/4] Remove useless calls to flush some stats
@ 2026-01-06 11:06  Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 12+ messages in thread

From: Bertrand Drouvot @ 2026-01-06 11:06 UTC (permalink / raw)

Now that some stats can be flushed outside of transaction boundaries, remove
useless calls to report/flush some stats. Those calls were in place because
before commit <XXXX> stats were flushed only at transaction boundaries.

Note that:

- it reverts 039549d70f6 (it just keeps its tests)
- it can't be done for checkpointer and bgworker for example because they don't
have a flush callback to call
- it can't be done for auxiliary process (walsummarizer for example) because they
currently do not register the new timeout handler
---
 src/backend/replication/walreceiver.c        | 10 ------
 src/backend/replication/walsender.c          | 36 ++------------------
 src/backend/utils/activity/pgstat_relation.c | 13 -------
 src/test/recovery/t/001_stream_rep.pl        |  1 +
 src/test/subscription/t/001_rep_changes.pl   |  1 +
 5 files changed, 4 insertions(+), 57 deletions(-)
  69.9% src/backend/replication/
  22.8% src/backend/utils/activity/
   3.5% src/test/recovery/t/
   3.6% src/test/subscription/t/

diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index 6970af3f3ff..dcbe3517b46 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -565,16 +565,6 @@ WalReceiverMain(const void *startup_data, size_t startup_data_len)
 					 */
 					bool		requestReply = false;
 
-					/*
-					 * Report pending statistics to the cumulative stats
-					 * system.  This location is useful for the report as it
-					 * is not within a tight loop in the WAL receiver, to
-					 * avoid bloating pgstats with requests, while also making
-					 * sure that the reports happen each time a status update
-					 * is sent.
-					 */
-					pgstat_report_wal(false);
-
 					/*
 					 * Check if time since last receive from primary has
 					 * reached the configured limit.
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index a0e6a3d200c..74102def9c7 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -94,14 +94,10 @@
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 #include "utils/pg_lsn.h"
-#include "utils/pgstat_internal.h"
 #include "utils/ps_status.h"
 #include "utils/timeout.h"
 #include "utils/timestamp.h"
 
-/* Minimum interval used by walsender for stats flushes, in ms */
-#define WALSENDER_STATS_FLUSH_INTERVAL         1000
-
 /*
  * Maximum data payload in a WAL data message.  Must be >= XLOG_BLCKSZ.
  *
@@ -1825,7 +1821,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	int			wakeEvents;
 	uint32		wait_event = 0;
 	static XLogRecPtr RecentFlushPtr = InvalidXLogRecPtr;
-	TimestampTz last_flush = 0;
 
 	/*
 	 * Fast path to avoid acquiring the spinlock in case we already know we
@@ -1846,7 +1841,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 	{
 		bool		wait_for_standby_at_stop = false;
 		long		sleeptime;
-		TimestampTz now;
 
 		/* Clear any already-pending wakeups */
 		ResetLatch(MyLatch);
@@ -1957,8 +1951,7 @@ WalSndWaitForWal(XLogRecPtr loc)
 		 * new WAL to be generated.  (But if we have nothing to send, we don't
 		 * want to wake on socket-writable.)
 		 */
-		now = GetCurrentTimestamp();
-		sleeptime = WalSndComputeSleeptime(now);
+		sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 		wakeEvents = WL_SOCKET_READABLE;
 
@@ -1967,15 +1960,6 @@ WalSndWaitForWal(XLogRecPtr loc)
 
 		Assert(wait_event != 0);
 
-		/* Report IO statistics, if needed */
-		if (TimestampDifferenceExceeds(last_flush, now,
-									   WALSENDER_STATS_FLUSH_INTERVAL))
-		{
-			pgstat_flush_io(false);
-			(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
-			last_flush = now;
-		}
-
 		WalSndWait(wakeEvents, sleeptime, wait_event);
 	}
 
@@ -2878,8 +2862,6 @@ WalSndCheckTimeOut(void)
 static void
 WalSndLoop(WalSndSendDataCallback send_data)
 {
-	TimestampTz last_flush = 0;
-
 	/*
 	 * Initialize the last reply timestamp. That enables timeout processing
 	 * from hereon.
@@ -2974,9 +2956,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		 * WalSndWaitForWal() handle any other blocking; idle receivers need
 		 * its additional actions.  For physical replication, also block if
 		 * caught up; its send_data does not block.
-		 *
-		 * The IO statistics are reported in WalSndWaitForWal() for the
-		 * logical WAL senders.
 		 */
 		if ((WalSndCaughtUp && send_data != XLogSendLogical &&
 			 !streamingDoneSending) ||
@@ -2984,7 +2963,6 @@ WalSndLoop(WalSndSendDataCallback send_data)
 		{
 			long		sleeptime;
 			int			wakeEvents;
-			TimestampTz now;
 
 			if (!streamingDoneReceiving)
 				wakeEvents = WL_SOCKET_READABLE;
@@ -2995,21 +2973,11 @@ WalSndLoop(WalSndSendDataCallback send_data)
 			 * Use fresh timestamp, not last_processing, to reduce the chance
 			 * of reaching wal_sender_timeout before sending a keepalive.
 			 */
-			now = GetCurrentTimestamp();
-			sleeptime = WalSndComputeSleeptime(now);
+			sleeptime = WalSndComputeSleeptime(GetCurrentTimestamp());
 
 			if (pq_is_send_pending())
 				wakeEvents |= WL_SOCKET_WRITEABLE;
 
-			/* Report IO statistics, if needed */
-			if (TimestampDifferenceExceeds(last_flush, now,
-										   WALSENDER_STATS_FLUSH_INTERVAL))
-			{
-				pgstat_flush_io(false);
-				(void) pgstat_flush_backend(false, PGSTAT_BACKEND_FLUSH_IO);
-				last_flush = now;
-			}
-
 			/* Sleep until something happens or we time out */
 			WalSndWait(wakeEvents, sleeptime, WAIT_EVENT_WAL_SENDER_MAIN);
 		}
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index bc8c43b96aa..feae2ae5f44 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -260,15 +260,6 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	}
 
 	pgstat_unlock_entry(entry_ref);
-
-	/*
-	 * Flush IO statistics now. pgstat_report_stat() will flush IO stats,
-	 * however this will not be called until after an entire autovacuum cycle
-	 * 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);
 }
 
 /*
@@ -360,10 +351,6 @@ 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);
 }
 
 /*
diff --git a/src/test/recovery/t/001_stream_rep.pl b/src/test/recovery/t/001_stream_rep.pl
index e9ac67813c7..c058a5f9b1f 100644
--- a/src/test/recovery/t/001_stream_rep.pl
+++ b/src/test/recovery/t/001_stream_rep.pl
@@ -15,6 +15,7 @@ my $node_primary = PostgreSQL::Test::Cluster->new('primary');
 $node_primary->init(
 	allows_streaming => 1,
 	auth_extra => [ '--create-role' => 'repl_role' ]);
+$node_primary->append_conf('postgresql.conf', "stats_flush_interval= '1s'");
 $node_primary->start;
 my $backup_name = 'my_backup';
 
diff --git a/src/test/subscription/t/001_rep_changes.pl b/src/test/subscription/t/001_rep_changes.pl
index d7e62e4d488..dda872f7074 100644
--- a/src/test/subscription/t/001_rep_changes.pl
+++ b/src/test/subscription/t/001_rep_changes.pl
@@ -11,6 +11,7 @@ use Test::More;
 # Initialize publisher node
 my $node_publisher = PostgreSQL::Test::Cluster->new('publisher');
 $node_publisher->init(allows_streaming => 'logical');
+$node_publisher->append_conf('postgresql.conf', "stats_flush_interval= '1s'");
 $node_publisher->start;
 
 # Create subscriber node
-- 
2.34.1


--wR/mWGXukst4NraF
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0004-Add-FLUSH_MIXED-support-and-implement-it-for-RELA.patch"



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

end of thread, other threads:[~2026-01-06 11:06 UTC | newest]

Thread overview: 12+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2024-04-28 11:00 [PATCH v17 2/8] Row pattern recognition patch (parse/analysis). Tatsuo Ishii <[email protected]>
2026-01-06 11:06 [PATCH v11 4/5] Remove useless calls to flush some stats Bertrand Drouvot <[email protected]>
2026-01-06 11:06 [PATCH v2 2/3] Remove useless calls to flush some stats Bertrand Drouvot <[email protected]>
2026-01-06 11:06 [PATCH v8 4/5] Remove useless calls to flush some stats Bertrand Drouvot <[email protected]>
2026-01-06 11:06 [PATCH v10 4/5] Remove useless calls to flush some stats Bertrand Drouvot <[email protected]>
2026-01-06 11:06 [PATCH v1 2/3] Remove useless calls to flush some stats Bertrand Drouvot <[email protected]>
2026-01-06 11:06 [PATCH v3 2/3] Remove useless calls to flush some stats Bertrand Drouvot <[email protected]>
2026-01-06 11:06 [PATCH v4 3/4] Remove useless calls to flush some stats Bertrand Drouvot <[email protected]>
2026-01-06 11:06 [PATCH v5 3/4] Remove useless calls to flush some stats Bertrand Drouvot <[email protected]>
2026-01-06 11:06 [PATCH v6 4/5] Remove useless calls to flush some stats Bertrand Drouvot <[email protected]>
2026-01-06 11:06 [PATCH v7 4/5] Remove useless calls to flush some stats Bertrand Drouvot <[email protected]>
2026-01-06 11:06 [PATCH v9 4/5] Remove useless calls to flush some stats 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