v6-0003-instrumentation-Separate-per-node-and-trigger-log.patch

application/octet-stream

Filename: v6-0003-instrumentation-Separate-per-node-and-trigger-log.patch
Type: application/octet-stream
Part: 1
Message: Re: Stack-based tracking of per-node WAL/buffer usage

Patch

Same data as JSON: GET /api/v1/attachments/:id/patch the parsed metadata as JSON — format, series position, per-file stats; never the diff bytes. API reference →
Format: format-patch
Series: patch v6-0003
Subject: instrumentation: Separate per-node and trigger logic from other uses
File+
contrib/auto_explain/auto_explain.c 1 7
contrib/pg_stat_statements/pg_stat_statements.c 1 7
contrib/postgres_fdw/postgres_fdw.c 1 1
src/backend/commands/explain.c 12 15
src/backend/commands/trigger.c 11 11
src/backend/executor/execMain.c 5 5
src/backend/executor/execParallel.c 14 10
src/backend/executor/execProcnode.c 2 2
src/backend/executor/instrument.c 101 22
src/include/executor/instrument.h 54 12
src/include/nodes/execnodes.h 5 3
src/tools/pgindent/typedefs.list 3 1
From 0bc83c0cac3f2c9987a7bb67cdb1e5a15e8701b9 Mon Sep 17 00:00:00 2001
From: Lukas Fittl <lukas@fittl.com>
Date: Sat, 1 Mar 2025 19:31:30 -0800
Subject: [PATCH v6 3/8] instrumentation: Separate per-node and trigger logic
 from other uses

Previously different places (e.g. query "total time") were repurposing
the Instrumentation struct initially introduced for capturing per-node
statistics during execution. This overuse of the same struct is confusing,
e.g. by cluttering calls of InstrStartNode/InstrStopNode in unrelated
code paths, and prevents future refactorings.

Instead, simplify the Instrumentation struct to only track time and
WAL/buffer usage. Similarly, drop the use of InstrEndLoop outside of
per-node instrumentation - these calls were added without any apparent
benefit since the relevant fields were never read.

Introduce the NodeInstrumentation struct to carry forward the per-node
instrumentation information, and introduce TriggerInstrumentation to
capture trigger timing and firings (previously counted in "ntuples").
WorkerInstrumentation is renamed to WorkerNodeInstrumentation for clarity.

In passing, drop the "n" argument to InstrAlloc, as all remaining callers
need exactly one Instrumentation struct.

Author: Lukas Fittl <lukas@fittl.com>
Reviewed-by:
Discussion:
---
 contrib/auto_explain/auto_explain.c           |   8 +-
 .../pg_stat_statements/pg_stat_statements.c   |   8 +-
 contrib/postgres_fdw/postgres_fdw.c           |   2 +-
 src/backend/commands/explain.c                |  27 ++--
 src/backend/commands/trigger.c                |  22 ++--
 src/backend/executor/execMain.c               |  10 +-
 src/backend/executor/execParallel.c           |  24 ++--
 src/backend/executor/execProcnode.c           |   4 +-
 src/backend/executor/instrument.c             | 123 ++++++++++++++----
 src/include/executor/instrument.h             |  66 ++++++++--
 src/include/nodes/execnodes.h                 |   8 +-
 src/tools/pgindent/typedefs.list              |   4 +-
 12 files changed, 210 insertions(+), 96 deletions(-)

diff --git a/contrib/auto_explain/auto_explain.c b/contrib/auto_explain/auto_explain.c
index e856cd35a6f..39bf2543b70 100644
--- a/contrib/auto_explain/auto_explain.c
+++ b/contrib/auto_explain/auto_explain.c
@@ -315,7 +315,7 @@ explain_ExecutorStart(QueryDesc *queryDesc, int eflags)
 			MemoryContext oldcxt;
 
 			oldcxt = MemoryContextSwitchTo(queryDesc->estate->es_query_cxt);
-			queryDesc->totaltime = InstrAlloc(1, INSTRUMENT_ALL, false);
+			queryDesc->totaltime = InstrAlloc(INSTRUMENT_ALL);
 			MemoryContextSwitchTo(oldcxt);
 		}
 	}
@@ -381,12 +381,6 @@ explain_ExecutorEnd(QueryDesc *queryDesc)
 		 */
 		oldcxt = MemoryContextSwitchTo(queryDesc->estate->es_query_cxt);
 
-		/*
-		 * Make sure stats accumulation is done.  (Note: it's okay if several
-		 * levels of hook all do this.)
-		 */
-		InstrEndLoop(queryDesc->totaltime);
-
 		/* Log plan if duration is exceeded. */
 		msec = INSTR_TIME_GET_MILLISEC(queryDesc->totaltime->total);
 		if (msec >= auto_explain_log_min_duration)
diff --git a/contrib/pg_stat_statements/pg_stat_statements.c b/contrib/pg_stat_statements/pg_stat_statements.c
index 4a427533bd8..388b068ccec 100644
--- a/contrib/pg_stat_statements/pg_stat_statements.c
+++ b/contrib/pg_stat_statements/pg_stat_statements.c
@@ -1023,7 +1023,7 @@ pgss_ExecutorStart(QueryDesc *queryDesc, int eflags)
 			MemoryContext oldcxt;
 
 			oldcxt = MemoryContextSwitchTo(queryDesc->estate->es_query_cxt);
-			queryDesc->totaltime = InstrAlloc(1, INSTRUMENT_ALL, false);
+			queryDesc->totaltime = InstrAlloc(INSTRUMENT_ALL);
 			MemoryContextSwitchTo(oldcxt);
 		}
 	}
@@ -1082,12 +1082,6 @@ pgss_ExecutorEnd(QueryDesc *queryDesc)
 	if (queryId != INT64CONST(0) && queryDesc->totaltime &&
 		pgss_enabled(nesting_level))
 	{
-		/*
-		 * Make sure stats accumulation is done.  (Note: it's okay if several
-		 * levels of hook all do this.)
-		 */
-		InstrEndLoop(queryDesc->totaltime);
-
 		pgss_store(queryDesc->sourceText,
 				   queryId,
 				   queryDesc->plannedstmt->stmt_location,
diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c
index 60d90329a65..6f0cb2a285b 100644
--- a/contrib/postgres_fdw/postgres_fdw.c
+++ b/contrib/postgres_fdw/postgres_fdw.c
@@ -2778,7 +2778,7 @@ postgresIterateDirectModify(ForeignScanState *node)
 	if (!resultRelInfo->ri_projectReturning)
 	{
 		TupleTableSlot *slot = node->ss.ss_ScanTupleSlot;
-		Instrumentation *instr = node->ss.ps.instrument;
+		NodeInstrumentation *instr = node->ss.ps.instrument;
 
 		Assert(!dmstate->has_returning);
 
diff --git a/src/backend/commands/explain.c b/src/backend/commands/explain.c
index 93918a223b8..d7f33644d79 100644
--- a/src/backend/commands/explain.c
+++ b/src/backend/commands/explain.c
@@ -1099,18 +1099,15 @@ report_triggers(ResultRelInfo *rInfo, bool show_relname, ExplainState *es)
 	for (nt = 0; nt < rInfo->ri_TrigDesc->numtriggers; nt++)
 	{
 		Trigger    *trig = rInfo->ri_TrigDesc->triggers + nt;
-		Instrumentation *instr = rInfo->ri_TrigInstrument + nt;
+		TriggerInstrumentation *tginstr = rInfo->ri_TrigInstrument + nt;
 		char	   *relname;
 		char	   *conname = NULL;
 
-		/* Must clean up instrumentation state */
-		InstrEndLoop(instr);
-
 		/*
 		 * We ignore triggers that were never invoked; they likely aren't
 		 * relevant to the current query type.
 		 */
-		if (instr->ntuples == 0)
+		if (tginstr->firings == 0)
 			continue;
 
 		ExplainOpenGroup("Trigger", NULL, true, es);
@@ -1135,11 +1132,11 @@ report_triggers(ResultRelInfo *rInfo, bool show_relname, ExplainState *es)
 			if (show_relname)
 				appendStringInfo(es->str, " on %s", relname);
 			if (es->timing)
-				appendStringInfo(es->str, ": time=%.3f calls=%.0f\n",
-								 INSTR_TIME_GET_MILLISEC(instr->total),
-								 instr->ntuples);
+				appendStringInfo(es->str, ": time=%.3f calls=%d\n",
+								 INSTR_TIME_GET_MILLISEC(tginstr->instr.total),
+								 tginstr->firings);
 			else
-				appendStringInfo(es->str, ": calls=%.0f\n", instr->ntuples);
+				appendStringInfo(es->str, ": calls=%d\n", tginstr->firings);
 		}
 		else
 		{
@@ -1149,9 +1146,9 @@ report_triggers(ResultRelInfo *rInfo, bool show_relname, ExplainState *es)
 			ExplainPropertyText("Relation", relname, es);
 			if (es->timing)
 				ExplainPropertyFloat("Time", "ms",
-									 INSTR_TIME_GET_MILLISEC(instr->total), 3,
+									 INSTR_TIME_GET_MILLISEC(tginstr->instr.total), 3,
 									 es);
-			ExplainPropertyFloat("Calls", NULL, instr->ntuples, 0, es);
+			ExplainPropertyInteger("Calls", NULL, tginstr->firings, es);
 		}
 
 		if (conname)
@@ -1891,11 +1888,11 @@ ExplainNode(PlanState *planstate, List *ancestors,
 	/* prepare per-worker general execution details */
 	if (es->workers_state && es->verbose)
 	{
-		WorkerInstrumentation *w = planstate->worker_instrument;
+		WorkerNodeInstrumentation *w = planstate->worker_instrument;
 
 		for (int n = 0; n < w->num_workers; n++)
 		{
-			Instrumentation *instrument = &w->instrument[n];
+			NodeInstrumentation *instrument = &w->instrument[n];
 			double		nloops = instrument->nloops;
 			double		startup_ms;
 			double		total_ms;
@@ -2298,11 +2295,11 @@ ExplainNode(PlanState *planstate, List *ancestors,
 	/* Prepare per-worker buffer/WAL usage */
 	if (es->workers_state && (es->buffers || es->wal) && es->verbose)
 	{
-		WorkerInstrumentation *w = planstate->worker_instrument;
+		WorkerNodeInstrumentation *w = planstate->worker_instrument;
 
 		for (int n = 0; n < w->num_workers; n++)
 		{
-			Instrumentation *instrument = &w->instrument[n];
+			NodeInstrumentation *instrument = &w->instrument[n];
 			double		nloops = instrument->nloops;
 
 			if (nloops <= 0)
diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index 98d402c0a3b..c3360073141 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -90,7 +90,7 @@ static bool TriggerEnabled(EState *estate, ResultRelInfo *relinfo,
 static HeapTuple ExecCallTriggerFunc(TriggerData *trigdata,
 									 int tgindx,
 									 FmgrInfo *finfo,
-									 Instrumentation *instr,
+									 TriggerInstrumentation *instr,
 									 MemoryContext per_tuple_context);
 static void AfterTriggerSaveEvent(EState *estate, ResultRelInfo *relinfo,
 								  ResultRelInfo *src_partinfo,
@@ -2309,7 +2309,7 @@ static HeapTuple
 ExecCallTriggerFunc(TriggerData *trigdata,
 					int tgindx,
 					FmgrInfo *finfo,
-					Instrumentation *instr,
+					TriggerInstrumentation *instr,
 					MemoryContext per_tuple_context)
 {
 	LOCAL_FCINFO(fcinfo, 0);
@@ -2344,7 +2344,7 @@ ExecCallTriggerFunc(TriggerData *trigdata,
 	 * If doing EXPLAIN ANALYZE, start charging time to this trigger.
 	 */
 	if (instr)
-		InstrStartNode(instr + tgindx);
+		InstrStartTrigger(instr + tgindx);
 
 	/*
 	 * Do the function evaluation in the per-tuple memory context, so that
@@ -2389,10 +2389,10 @@ ExecCallTriggerFunc(TriggerData *trigdata,
 
 	/*
 	 * If doing EXPLAIN ANALYZE, stop charging time to this trigger, and count
-	 * one "tuple returned" (really the number of firings).
+	 * the firing of the trigger.
 	 */
 	if (instr)
-		InstrStopNode(instr + tgindx, 1);
+		InstrStopTrigger(instr + tgindx, 1);
 
 	return (HeapTuple) DatumGetPointer(result);
 }
@@ -3936,7 +3936,7 @@ static void AfterTriggerExecute(EState *estate,
 								ResultRelInfo *dst_relInfo,
 								TriggerDesc *trigdesc,
 								FmgrInfo *finfo,
-								Instrumentation *instr,
+								TriggerInstrumentation *instr,
 								MemoryContext per_tuple_context,
 								TupleTableSlot *trig_tuple_slot1,
 								TupleTableSlot *trig_tuple_slot2);
@@ -4330,7 +4330,7 @@ AfterTriggerExecute(EState *estate,
 					ResultRelInfo *src_relInfo,
 					ResultRelInfo *dst_relInfo,
 					TriggerDesc *trigdesc,
-					FmgrInfo *finfo, Instrumentation *instr,
+					FmgrInfo *finfo, TriggerInstrumentation *instr,
 					MemoryContext per_tuple_context,
 					TupleTableSlot *trig_tuple_slot1,
 					TupleTableSlot *trig_tuple_slot2)
@@ -4371,7 +4371,7 @@ AfterTriggerExecute(EState *estate,
 	 * to include time spent re-fetching tuples in the trigger cost.
 	 */
 	if (instr)
-		InstrStartNode(instr + tgindx);
+		InstrStartTrigger(instr + tgindx);
 
 	/*
 	 * Fetch the required tuple(s).
@@ -4588,10 +4588,10 @@ AfterTriggerExecute(EState *estate,
 
 	/*
 	 * If doing EXPLAIN ANALYZE, stop charging time to this trigger, and count
-	 * one "tuple returned" (really the number of firings).
+	 * the firing of the trigger.
 	 */
 	if (instr)
-		InstrStopNode(instr + tgindx, 1);
+		InstrStopTrigger(instr + tgindx, 1);
 }
 
 
@@ -4707,7 +4707,7 @@ afterTriggerInvokeEvents(AfterTriggerEventList *events,
 	Relation	rel = NULL;
 	TriggerDesc *trigdesc = NULL;
 	FmgrInfo   *finfo = NULL;
-	Instrumentation *instr = NULL;
+	TriggerInstrumentation *instr = NULL;
 	TupleTableSlot *slot1 = NULL,
 			   *slot2 = NULL;
 
diff --git a/src/backend/executor/execMain.c b/src/backend/executor/execMain.c
index bfd3ebc601e..c0b174cfbc0 100644
--- a/src/backend/executor/execMain.c
+++ b/src/backend/executor/execMain.c
@@ -331,7 +331,7 @@ standard_ExecutorRun(QueryDesc *queryDesc,
 
 	/* Allow instrumentation of Executor overall runtime */
 	if (queryDesc->totaltime)
-		InstrStartNode(queryDesc->totaltime);
+		InstrStart(queryDesc->totaltime);
 
 	/*
 	 * extract information from the query descriptor and the query feature.
@@ -383,7 +383,7 @@ standard_ExecutorRun(QueryDesc *queryDesc,
 		dest->rShutdown(dest);
 
 	if (queryDesc->totaltime)
-		InstrStopNode(queryDesc->totaltime, estate->es_processed);
+		InstrStop(queryDesc->totaltime);
 
 	MemoryContextSwitchTo(oldcontext);
 }
@@ -433,7 +433,7 @@ standard_ExecutorFinish(QueryDesc *queryDesc)
 
 	/* Allow instrumentation of Executor overall runtime */
 	if (queryDesc->totaltime)
-		InstrStartNode(queryDesc->totaltime);
+		InstrStart(queryDesc->totaltime);
 
 	/* Run ModifyTable nodes to completion */
 	ExecPostprocessPlan(estate);
@@ -443,7 +443,7 @@ standard_ExecutorFinish(QueryDesc *queryDesc)
 		AfterTriggerEndQuery(estate);
 
 	if (queryDesc->totaltime)
-		InstrStopNode(queryDesc->totaltime, 0);
+		InstrStop(queryDesc->totaltime);
 
 	MemoryContextSwitchTo(oldcontext);
 
@@ -1270,7 +1270,7 @@ InitResultRelInfo(ResultRelInfo *resultRelInfo,
 		resultRelInfo->ri_TrigWhenExprs = (ExprState **)
 			palloc0_array(ExprState *, n);
 		if (instrument_options)
-			resultRelInfo->ri_TrigInstrument = InstrAlloc(n, instrument_options, false);
+			resultRelInfo->ri_TrigInstrument = InstrAllocTrigger(n, instrument_options);
 	}
 	else
 	{
diff --git a/src/backend/executor/execParallel.c b/src/backend/executor/execParallel.c
index f87978c137e..fb9a4afbbf1 100644
--- a/src/backend/executor/execParallel.c
+++ b/src/backend/executor/execParallel.c
@@ -86,7 +86,7 @@ typedef struct FixedParallelExecutorState
  * instrument_options: Same meaning here as in instrument.c.
  *
  * instrument_offset: Offset, relative to the start of this structure,
- * of the first Instrumentation object.  This will depend on the length of
+ * of the first NodeInstrumentation object.  This will depend on the length of
  * the plan_node_id array.
  *
  * num_workers: Number of workers.
@@ -103,11 +103,15 @@ struct SharedExecutorInstrumentation
 	int			num_workers;
 	int			num_plan_nodes;
 	int			plan_node_id[FLEXIBLE_ARRAY_MEMBER];
-	/* array of num_plan_nodes * num_workers Instrumentation objects follows */
+
+	/*
+	 * array of num_plan_nodes * num_workers NodeInstrumentation objects
+	 * follows
+	 */
 };
 #define GetInstrumentationArray(sei) \
 	(StaticAssertVariableIsOfTypeMacro(sei, SharedExecutorInstrumentation *), \
-	 (Instrumentation *) (((char *) sei) + sei->instrument_offset))
+	 (NodeInstrumentation *) (((char *) sei) + sei->instrument_offset))
 
 /* Context object for ExecParallelEstimate. */
 typedef struct ExecParallelEstimateContext
@@ -724,7 +728,7 @@ ExecInitParallelPlan(PlanState *planstate, EState *estate,
 		instrumentation_len = MAXALIGN(instrumentation_len);
 		instrument_offset = instrumentation_len;
 		instrumentation_len +=
-			mul_size(sizeof(Instrumentation),
+			mul_size(sizeof(NodeInstrumentation),
 					 mul_size(e.nnodes, nworkers));
 		shm_toc_estimate_chunk(&pcxt->estimator, instrumentation_len);
 		shm_toc_estimate_keys(&pcxt->estimator, 1);
@@ -810,7 +814,7 @@ ExecInitParallelPlan(PlanState *planstate, EState *estate,
 	 */
 	if (estate->es_instrument)
 	{
-		Instrumentation *instrument;
+		NodeInstrumentation *instrument;
 		int			i;
 
 		instrumentation = shm_toc_allocate(pcxt->toc, instrumentation_len);
@@ -820,7 +824,7 @@ ExecInitParallelPlan(PlanState *planstate, EState *estate,
 		instrumentation->num_plan_nodes = e.nnodes;
 		instrument = GetInstrumentationArray(instrumentation);
 		for (i = 0; i < nworkers * e.nnodes; ++i)
-			InstrInit(&instrument[i], estate->es_instrument);
+			InstrInitNode(&instrument[i], estate->es_instrument);
 		shm_toc_insert(pcxt->toc, PARALLEL_KEY_INSTRUMENTATION,
 					   instrumentation);
 		pei->instrumentation = instrumentation;
@@ -1052,7 +1056,7 @@ static bool
 ExecParallelRetrieveInstrumentation(PlanState *planstate,
 									SharedExecutorInstrumentation *instrumentation)
 {
-	Instrumentation *instrument;
+	NodeInstrumentation *instrument;
 	int			i;
 	int			n;
 	int			ibytes;
@@ -1080,9 +1084,9 @@ ExecParallelRetrieveInstrumentation(PlanState *planstate,
 	 * Switch into per-query memory context.
 	 */
 	oldcontext = MemoryContextSwitchTo(planstate->state->es_query_cxt);
-	ibytes = mul_size(instrumentation->num_workers, sizeof(Instrumentation));
+	ibytes = mul_size(instrumentation->num_workers, sizeof(NodeInstrumentation));
 	planstate->worker_instrument =
-		palloc(ibytes + offsetof(WorkerInstrumentation, instrument));
+		palloc(ibytes + offsetof(WorkerNodeInstrumentation, instrument));
 	MemoryContextSwitchTo(oldcontext);
 
 	planstate->worker_instrument->num_workers = instrumentation->num_workers;
@@ -1312,7 +1316,7 @@ ExecParallelReportInstrumentation(PlanState *planstate,
 {
 	int			i;
 	int			plan_node_id = planstate->plan->plan_node_id;
-	Instrumentation *instrument;
+	NodeInstrumentation *instrument;
 
 	InstrEndLoop(planstate->instrument);
 
diff --git a/src/backend/executor/execProcnode.c b/src/backend/executor/execProcnode.c
index 7e40b852517..1846661b503 100644
--- a/src/backend/executor/execProcnode.c
+++ b/src/backend/executor/execProcnode.c
@@ -413,8 +413,8 @@ ExecInitNode(Plan *node, EState *estate, int eflags)
 
 	/* Set up instrumentation for this node if requested */
 	if (estate->es_instrument)
-		result->instrument = InstrAlloc(1, estate->es_instrument,
-										result->async_capable);
+		result->instrument = InstrAllocNode(estate->es_instrument,
+											result->async_capable);
 
 	return result;
 }
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index 4c3930a4f86..34daadc88fc 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -26,38 +26,117 @@ static void BufferUsageAdd(BufferUsage *dst, const BufferUsage *add);
 static void WalUsageAdd(WalUsage *dst, WalUsage *add);
 
 
-/* Allocate new instrumentation structure(s) */
+/* General purpose instrumentation handling */
 Instrumentation *
-InstrAlloc(int n, int instrument_options, bool async_mode)
+InstrAlloc(int instrument_options)
 {
 	Instrumentation *instr;
 
 	/* initialize all fields to zeroes, then modify as needed */
-	instr = palloc0(n * sizeof(Instrumentation));
+	instr = palloc0(sizeof(Instrumentation));
 	if (instrument_options & (INSTRUMENT_BUFFERS | INSTRUMENT_TIMER | INSTRUMENT_WAL))
 	{
-		bool		need_buffers = (instrument_options & INSTRUMENT_BUFFERS) != 0;
-		bool		need_wal = (instrument_options & INSTRUMENT_WAL) != 0;
-		bool		need_timer = (instrument_options & INSTRUMENT_TIMER) != 0;
-		int			i;
-
-		for (i = 0; i < n; i++)
-		{
-			instr[i].need_bufusage = need_buffers;
-			instr[i].need_walusage = need_wal;
-			instr[i].need_timer = need_timer;
-			instr[i].async_mode = async_mode;
-		}
+		instr->need_bufusage = (instrument_options & INSTRUMENT_BUFFERS) != 0;
+		instr->need_walusage = (instrument_options & INSTRUMENT_WAL) != 0;
+		instr->need_timer = (instrument_options & INSTRUMENT_TIMER) != 0;
 	}
 
 	return instr;
 }
 
+void
+InstrStart(Instrumentation *instr)
+{
+	if (instr->need_timer &&
+		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
+		elog(ERROR, "InstrStart called twice in a row");
+
+	if (instr->need_bufusage)
+		instr->bufusage_start = pgBufferUsage;
+
+	if (instr->need_walusage)
+		instr->walusage_start = pgWalUsage;
+}
+
+void
+InstrStop(Instrumentation *instr)
+{
+	instr_time	endtime;
+
+	/* let's update the time only if the timer was requested */
+	if (instr->need_timer)
+	{
+		if (INSTR_TIME_IS_ZERO(instr->starttime))
+			elog(ERROR, "InstrStop called without start");
+
+		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_ACCUM_DIFF(instr->total, endtime, instr->starttime);
+
+		INSTR_TIME_SET_ZERO(instr->starttime);
+	}
+
+	/* Add delta of buffer usage since entry to node's totals */
+	if (instr->need_bufusage)
+		BufferUsageAccumDiff(&instr->bufusage,
+							 &pgBufferUsage, &instr->bufusage_start);
+
+	if (instr->need_walusage)
+		WalUsageAccumDiff(&instr->walusage,
+						  &pgWalUsage, &instr->walusage_start);
+}
+
+/* Trigger instrumentation handling */
+TriggerInstrumentation *
+InstrAllocTrigger(int n, int instrument_options)
+{
+	TriggerInstrumentation *tginstr = palloc0(n * sizeof(TriggerInstrumentation));
+	bool		need_buffers = (instrument_options & INSTRUMENT_BUFFERS) != 0;
+	bool		need_wal = (instrument_options & INSTRUMENT_WAL) != 0;
+	bool		need_timer = (instrument_options & INSTRUMENT_TIMER) != 0;
+	int			i;
+
+	for (i = 0; i < n; i++)
+	{
+		tginstr[i].instr.need_bufusage = need_buffers;
+		tginstr[i].instr.need_walusage = need_wal;
+		tginstr[i].instr.need_timer = need_timer;
+	}
+
+	return tginstr;
+}
+
+void
+InstrStartTrigger(TriggerInstrumentation *tginstr)
+{
+	InstrStart(&tginstr->instr);
+}
+
+void
+InstrStopTrigger(TriggerInstrumentation *tginstr, int firings)
+{
+	InstrStop(&tginstr->instr);
+	tginstr->firings += firings;
+}
+
+/* Node instrumentation handling */
+
+/* Allocate new node instrumentation structure */
+NodeInstrumentation *
+InstrAllocNode(int instrument_options, bool async_mode)
+{
+	NodeInstrumentation *instr = palloc(sizeof(NodeInstrumentation));
+
+	InstrInitNode(instr, instrument_options);
+	instr->async_mode = async_mode;
+
+	return instr;
+}
+
 /* Initialize a pre-allocated instrumentation structure. */
 void
-InstrInit(Instrumentation *instr, int instrument_options)
+InstrInitNode(NodeInstrumentation *instr, int instrument_options)
 {
-	memset(instr, 0, sizeof(Instrumentation));
+	memset(instr, 0, sizeof(NodeInstrumentation));
 	instr->need_bufusage = (instrument_options & INSTRUMENT_BUFFERS) != 0;
 	instr->need_walusage = (instrument_options & INSTRUMENT_WAL) != 0;
 	instr->need_timer = (instrument_options & INSTRUMENT_TIMER) != 0;
@@ -65,7 +144,7 @@ InstrInit(Instrumentation *instr, int instrument_options)
 
 /* Entry to a plan node */
 void
-InstrStartNode(Instrumentation *instr)
+InstrStartNode(NodeInstrumentation *instr)
 {
 	if (instr->need_timer &&
 		!INSTR_TIME_SET_CURRENT_LAZY(instr->starttime))
@@ -81,7 +160,7 @@ InstrStartNode(Instrumentation *instr)
 
 /* Exit from a plan node */
 void
-InstrStopNode(Instrumentation *instr, double nTuples)
+InstrStopNode(NodeInstrumentation *instr, double nTuples)
 {
 	double		save_tuplecount = instr->tuplecount;
 	instr_time	endtime;
@@ -129,7 +208,7 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 
 /* Update tuple count */
 void
-InstrUpdateTupleCount(Instrumentation *instr, double nTuples)
+InstrUpdateTupleCount(NodeInstrumentation *instr, double nTuples)
 {
 	/* count the returned tuples */
 	instr->tuplecount += nTuples;
@@ -137,7 +216,7 @@ InstrUpdateTupleCount(Instrumentation *instr, double nTuples)
 
 /* Finish a run cycle for a plan node */
 void
-InstrEndLoop(Instrumentation *instr)
+InstrEndLoop(NodeInstrumentation *instr)
 {
 	/* Skip if nothing has happened, or already shut down */
 	if (!instr->running)
@@ -162,7 +241,7 @@ InstrEndLoop(Instrumentation *instr)
 
 /* aggregate instrumentation information */
 void
-InstrAggNode(Instrumentation *dst, Instrumentation *add)
+InstrAggNode(NodeInstrumentation *dst, NodeInstrumentation *add)
 {
 	if (!dst->running && add->running)
 	{
diff --git a/src/include/executor/instrument.h b/src/include/executor/instrument.h
index 64e91373b5d..16688b5fdb4 100644
--- a/src/include/executor/instrument.h
+++ b/src/include/executor/instrument.h
@@ -67,7 +67,40 @@ typedef enum InstrumentOption
 	INSTRUMENT_ALL = PG_INT32_MAX
 } InstrumentOption;
 
+/*
+ * General purpose instrumentation that can capture time and WAL/buffer usage
+ *
+ * Initialized through InstrAlloc, followed by one or more calls to a pair of
+ * InstrStart/InstrStop (activity is measured inbetween).
+ */
 typedef struct Instrumentation
+{
+	/* Parameters set at creation: */
+	bool		need_timer;		/* true if we need timer data */
+	bool		need_bufusage;	/* true if we need buffer usage data */
+	bool		need_walusage;	/* true if we need WAL usage data */
+	/* Internal state keeping: */
+	instr_time	starttime;		/* start time of last InstrStart */
+	BufferUsage bufusage_start; /* buffer usage at start */
+	WalUsage	walusage_start; /* WAL usage at start */
+	/* Accumulated statistics: */
+	instr_time	total;			/* total runtime */
+	BufferUsage bufusage;		/* total buffer usage */
+	WalUsage	walusage;		/* total WAL usage */
+} Instrumentation;
+
+/* Trigger instrumentation */
+typedef struct TriggerInstrumentation
+{
+	Instrumentation instr;
+	int			firings;		/* number of times the instrumented trigger
+								 * was fired */
+} TriggerInstrumentation;
+
+/*
+ * Specialized instrumentation for per-node execution statistics
+ */
+typedef struct NodeInstrumentation
 {
 	/* Parameters set at node creation: */
 	bool		need_timer;		/* true if we need timer data */
@@ -92,25 +125,34 @@ typedef struct Instrumentation
 	double		nfiltered2;		/* # of tuples removed by "other" quals */
 	BufferUsage bufusage;		/* total buffer usage */
 	WalUsage	walusage;		/* total WAL usage */
-} Instrumentation;
+} NodeInstrumentation;
 
-typedef struct WorkerInstrumentation
+typedef struct WorkerNodeInstrumentation
 {
 	int			num_workers;	/* # of structures that follow */
-	Instrumentation instrument[FLEXIBLE_ARRAY_MEMBER];
-} WorkerInstrumentation;
+	NodeInstrumentation instrument[FLEXIBLE_ARRAY_MEMBER];
+} WorkerNodeInstrumentation;
 
 extern PGDLLIMPORT BufferUsage pgBufferUsage;
 extern PGDLLIMPORT WalUsage pgWalUsage;
 
-extern Instrumentation *InstrAlloc(int n, int instrument_options,
-								   bool async_mode);
-extern void InstrInit(Instrumentation *instr, int instrument_options);
-extern void InstrStartNode(Instrumentation *instr);
-extern void InstrStopNode(Instrumentation *instr, double nTuples);
-extern void InstrUpdateTupleCount(Instrumentation *instr, double nTuples);
-extern void InstrEndLoop(Instrumentation *instr);
-extern void InstrAggNode(Instrumentation *dst, Instrumentation *add);
+extern Instrumentation *InstrAlloc(int instrument_options);
+extern void InstrStart(Instrumentation *instr);
+extern void InstrStop(Instrumentation *instr);
+
+extern TriggerInstrumentation *InstrAllocTrigger(int n, int instrument_options);
+extern void InstrStartTrigger(TriggerInstrumentation *tginstr);
+extern void InstrStopTrigger(TriggerInstrumentation *tginstr, int firings);
+
+extern NodeInstrumentation *InstrAllocNode(int instrument_options,
+										   bool async_mode);
+extern void InstrInitNode(NodeInstrumentation *instr, int instrument_options);
+extern void InstrStartNode(NodeInstrumentation *instr);
+extern void InstrStopNode(NodeInstrumentation *instr, double nTuples);
+extern void InstrUpdateTupleCount(NodeInstrumentation *instr, double nTuples);
+extern void InstrEndLoop(NodeInstrumentation *instr);
+extern void InstrAggNode(NodeInstrumentation *dst, NodeInstrumentation *add);
+
 extern void InstrStartParallelQuery(void);
 extern void InstrEndParallelQuery(BufferUsage *bufusage, WalUsage *walusage);
 extern void InstrAccumParallelQuery(BufferUsage *bufusage, WalUsage *walusage);
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index 63c067d5aae..605c7a6cc39 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -524,7 +524,7 @@ typedef struct ResultRelInfo
 	ExprState **ri_TrigWhenExprs;
 
 	/* optional runtime measurements for triggers */
-	Instrumentation *ri_TrigInstrument;
+	TriggerInstrumentation *ri_TrigInstrument;
 
 	/* On-demand created slots for triggers / returning processing */
 	TupleTableSlot *ri_ReturningSlot;	/* for trigger output tuples */
@@ -1175,8 +1175,10 @@ typedef struct PlanState
 	ExecProcNodeMtd ExecProcNodeReal;	/* actual function, if above is a
 										 * wrapper */
 
-	Instrumentation *instrument;	/* Optional runtime stats for this node */
-	WorkerInstrumentation *worker_instrument;	/* per-worker instrumentation */
+	NodeInstrumentation *instrument;	/* Optional runtime stats for this
+										 * node */
+	WorkerNodeInstrumentation *worker_instrument;	/* per-worker
+													 * instrumentation */
 
 	/* Per-worker JIT instrumentation */
 	struct SharedJitInstrumentation *worker_jit_instrument;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 241945734ec..e1075c709f5 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1784,6 +1784,7 @@ NextSampleBlock_function
 NextSampleTuple_function
 NextValueExpr
 Node
+NodeInstrumentation
 NodeTag
 NonEmptyRange
 NoneCompressorState
@@ -3155,6 +3156,7 @@ TriggerDesc
 TriggerEvent
 TriggerFlags
 TriggerInfo
+TriggerInstrumentation
 TriggerTransition
 TruncateStmt
 TsmRoutine
@@ -3375,9 +3377,9 @@ WorkTableScan
 WorkTableScanState
 WorkerInfo
 WorkerInfoData
-WorkerInstrumentation
 WorkerJobDumpPtrType
 WorkerJobRestorePtrType
+WorkerNodeInstrumentation
 Working_State
 WriteBufPtrType
 WriteBytePtrType
-- 
2.47.1