v8-0002-instrumentation-Separate-per-node-logic-from-othe.patch

From 9288c1968b8004ef0496cf8ed1a8e30c436d7450 Mon Sep 17 00:00:00 2001
From: Lukas Fittl <lukas@fittl.com>
Date: Sat, 7 Mar 2026 01:19:50 -0800
Subject: [PATCH v8 2/8] instrumentation: Separate per-node 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. 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                |  20 +--
 src/backend/executor/execMain.c               |   8 +-
 src/backend/executor/execParallel.c           |  24 +--
 src/backend/executor/execProcnode.c           |   4 +-
 src/backend/executor/instrument.c             | 142 ++++++++++++------
 src/include/executor/instrument.h             |  60 +++++---
 src/include/nodes/execnodes.h                 |   6 +-
 src/tools/pgindent/typedefs.list              |   3 +-
 11 files changed, 172 insertions(+), 113 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 09b13807d92..389181b8d9b 100644
--- a/src/backend/commands/explain.c
+++ b/src/backend/commands/explain.c
@@ -1835,7 +1835,7 @@ ExplainNode(PlanState *planstate, List *ancestors,
 	{
 		double		nloops = planstate->instrument->nloops;
 		double		startup_ms = INSTR_TIME_GET_MILLISEC(planstate->instrument->startup) / nloops;
-		double		total_ms = INSTR_TIME_GET_MILLISEC(planstate->instrument->total) / nloops;
+		double		total_ms = INSTR_TIME_GET_MILLISEC(planstate->instrument->instr.total) / nloops;
 		double		rows = planstate->instrument->ntuples / nloops;
 
 		if (es->format == EXPLAIN_FORMAT_TEXT)
@@ -1888,11 +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;
@@ -1901,7 +1901,7 @@ ExplainNode(PlanState *planstate, List *ancestors,
 			if (nloops <= 0)
 				continue;
 			startup_ms = INSTR_TIME_GET_MILLISEC(instrument->startup) / nloops;
-			total_ms = INSTR_TIME_GET_MILLISEC(instrument->total) / nloops;
+			total_ms = INSTR_TIME_GET_MILLISEC(instrument->instr.total) / nloops;
 			rows = instrument->ntuples / nloops;
 
 			ExplainOpenWorker(n, es);
@@ -2288,18 +2288,18 @@ ExplainNode(PlanState *planstate, List *ancestors,
 
 	/* Show buffer/WAL usage */
 	if (es->buffers && planstate->instrument)
-		show_buffer_usage(es, &planstate->instrument->bufusage);
+		show_buffer_usage(es, &planstate->instrument->instr.bufusage);
 	if (es->wal && planstate->instrument)
-		show_wal_usage(es, &planstate->instrument->walusage);
+		show_wal_usage(es, &planstate->instrument->instr.walusage);
 
 	/* 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)
@@ -2307,9 +2307,9 @@ ExplainNode(PlanState *planstate, List *ancestors,
 
 			ExplainOpenWorker(n, es);
 			if (es->buffers)
-				show_buffer_usage(es, &instrument->bufusage);
+				show_buffer_usage(es, &instrument->instr.bufusage);
 			if (es->wal)
-				show_wal_usage(es, &instrument->walusage);
+				show_wal_usage(es, &instrument->instr.walusage);
 			ExplainCloseWorker(n, es);
 		}
 	}
diff --git a/src/backend/executor/execMain.c b/src/backend/executor/execMain.c
index 1a3b8021600..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);
 
diff --git a/src/backend/executor/execParallel.c b/src/backend/executor/execParallel.c
index ac84af294c9..c153d5c1c3b 100644
--- a/src/backend/executor/execParallel.c
+++ b/src/backend/executor/execParallel.c
@@ -87,7 +87,7 @@ 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.
@@ -104,11 +104,15 @@ 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
@@ -725,7 +729,7 @@ 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);
@@ -811,7 +815,7 @@ ExecInitParallelPlan(PlanState *planstate, EState *estate,
 	 */
 	if (estate->es_instrument)
 	{
-		Instrumentation *instrument;
+		NodeInstrumentation *instrument;
 		int			i;
 
 		instrumentation = shm_toc_allocate(pcxt->toc, instrumentation_len);
@@ -821,7 +825,7 @@ 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;
@@ -1053,7 +1057,7 @@ static bool
 ExecParallelRetrieveInstrumentation(PlanState *planstate,
 									SharedExecutorInstrumentation *instrumentation)
 {
-	Instrumentation *instrument;
+	NodeInstrumentation *instrument;
 	int			i;
 	int			n;
 	int			ibytes;
@@ -1081,9 +1085,9 @@ 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;
@@ -1313,7 +1317,7 @@ 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 9354ad7be12..bc551f95a08 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -26,51 +26,30 @@ 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));
-	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;
-		}
-	}
-
+	Instrumentation *instr = palloc0(sizeof(Instrumentation));
+	InstrInitOptions(instr, instrument_options);
 	return instr;
 }
 
-/* Initialize a pre-allocated instrumentation structure. */
 void
-InstrInit(Instrumentation *instr, int instrument_options)
+InstrInitOptions(Instrumentation *instr, int instrument_options)
 {
-	memset(instr, 0, sizeof(Instrumentation));
 	instr->need_bufusage = (instrument_options & INSTRUMENT_BUFFERS) != 0;
 	instr->need_walusage = (instrument_options & INSTRUMENT_WAL) != 0;
 	instr->need_timer = (instrument_options & INSTRUMENT_TIMER) != 0;
 }
 
-/* Entry to a plan node */
 void
-InstrStartNode(Instrumentation *instr)
+InstrStart(Instrumentation *instr)
 {
 	if (instr->need_timer)
 	{
 		if (!INSTR_TIME_IS_ZERO(instr->starttime))
-			elog(ERROR, "InstrStartNode called twice in a row");
+			elog(ERROR, "InstrStart called twice in a row");
 		else
 			INSTR_TIME_SET_CURRENT(instr->starttime);
 	}
@@ -83,24 +62,19 @@ InstrStartNode(Instrumentation *instr)
 		instr->walusage_start = pgWalUsage;
 }
 
-/* Exit from a plan node */
 void
-InstrStopNode(Instrumentation *instr, double nTuples)
+InstrStop(Instrumentation *instr)
 {
-	double		save_tuplecount = instr->tuplecount;
 	instr_time	endtime;
 
-	/* count the returned tuples */
-	instr->tuplecount += nTuples;
-
 	/* let's update the time only if the timer was requested */
 	if (instr->need_timer)
 	{
 		if (INSTR_TIME_IS_ZERO(instr->starttime))
-			elog(ERROR, "InstrStopNode called without start");
+			elog(ERROR, "InstrStop called without start");
 
 		INSTR_TIME_SET_CURRENT(endtime);
-		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->starttime);
+		INSTR_TIME_ACCUM_DIFF(instr->total, endtime, instr->starttime);
 
 		INSTR_TIME_SET_ZERO(instr->starttime);
 	}
@@ -113,6 +87,74 @@ InstrStopNode(Instrumentation *instr, double nTuples)
 	if (instr->need_walusage)
 		WalUsageAccumDiff(&instr->walusage,
 						  &pgWalUsage, &instr->walusage_start);
+}
+
+/* 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
+InstrInitNode(NodeInstrumentation *instr, int instrument_options)
+{
+	memset(instr, 0, sizeof(NodeInstrumentation));
+	InstrInitOptions(&instr->instr, instrument_options);
+}
+
+/* Entry to a plan node */
+void
+InstrStartNode(NodeInstrumentation *instr)
+{
+	InstrStart(&instr->instr);
+}
+
+/* Exit from a plan node */
+void
+InstrStopNode(NodeInstrumentation *instr, double nTuples)
+{
+	double		save_tuplecount = instr->tuplecount;
+	instr_time	endtime;
+
+	/* count the returned tuples */
+	instr->tuplecount += nTuples;
+
+	/*
+	 * Update the time only if the timer was requested.
+	 *
+	 * Note this is different from InstrStop because total is only updated in
+	 * InstrEndLoop. We need the separate counter variable because we need to
+	 * calculate start-up time for the first tuple in each cycle, and then
+	 * accumulate it together.
+	 */
+	if (instr->instr.need_timer)
+	{
+		if (INSTR_TIME_IS_ZERO(instr->instr.starttime))
+			elog(ERROR, "InstrStopNode called without start");
+
+		INSTR_TIME_SET_CURRENT(endtime);
+		INSTR_TIME_ACCUM_DIFF(instr->counter, endtime, instr->instr.starttime);
+
+		INSTR_TIME_SET_ZERO(instr->instr.starttime);
+	}
+
+	/* Add delta of buffer usage since entry to node's totals */
+	if (instr->instr.need_bufusage)
+		BufferUsageAccumDiff(&instr->instr.bufusage,
+							 &pgBufferUsage, &instr->instr.bufusage_start);
+
+	if (instr->instr.need_walusage)
+		WalUsageAccumDiff(&instr->instr.walusage,
+						  &pgWalUsage, &instr->instr.walusage_start);
 
 	/* Is this the first tuple of this cycle? */
 	if (!instr->running)
@@ -133,7 +175,7 @@ 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;
@@ -141,24 +183,24 @@ 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)
 		return;
 
-	if (!INSTR_TIME_IS_ZERO(instr->starttime))
+	if (!INSTR_TIME_IS_ZERO(instr->instr.starttime))
 		elog(ERROR, "InstrEndLoop called on running node");
 
 	/* Accumulate per-cycle statistics into totals */
 	INSTR_TIME_ADD(instr->startup, instr->firsttuple);
-	INSTR_TIME_ADD(instr->total, instr->counter);
+	INSTR_TIME_ADD(instr->instr.total, instr->counter);
 	instr->ntuples += instr->tuplecount;
 	instr->nloops += 1;
 
 	/* Reset for next cycle (if any) */
 	instr->running = false;
-	INSTR_TIME_SET_ZERO(instr->starttime);
+	INSTR_TIME_SET_ZERO(instr->instr.starttime);
 	INSTR_TIME_SET_ZERO(instr->counter);
 	INSTR_TIME_SET_ZERO(instr->firsttuple);
 	instr->tuplecount = 0;
@@ -166,7 +208,7 @@ InstrEndLoop(Instrumentation *instr)
 
 /* aggregate instrumentation information */
 void
-InstrAggNode(Instrumentation *dst, Instrumentation *add)
+InstrAggNode(NodeInstrumentation *dst, NodeInstrumentation *add)
 {
 	if (!dst->running && add->running)
 	{
@@ -181,7 +223,7 @@ InstrAggNode(Instrumentation *dst, Instrumentation *add)
 
 	dst->tuplecount += add->tuplecount;
 	INSTR_TIME_ADD(dst->startup, add->startup);
-	INSTR_TIME_ADD(dst->total, add->total);
+	INSTR_TIME_ADD(dst->instr.total, add->instr.total);
 	dst->ntuples += add->ntuples;
 	dst->ntuples2 += add->ntuples2;
 	dst->nloops += add->nloops;
@@ -189,11 +231,11 @@ InstrAggNode(Instrumentation *dst, Instrumentation *add)
 	dst->nfiltered2 += add->nfiltered2;
 
 	/* Add delta of buffer usage since entry to node's totals */
-	if (dst->need_bufusage)
-		BufferUsageAdd(&dst->bufusage, &add->bufusage);
+	if (dst->instr.need_bufusage)
+		BufferUsageAdd(&dst->instr.bufusage, &add->instr.bufusage);
 
-	if (dst->need_walusage)
-		WalUsageAdd(&dst->walusage, &add->walusage);
+	if (dst->instr.need_walusage)
+		WalUsageAdd(&dst->instr.walusage, &add->instr.walusage);
 }
 
 /* Trigger instrumentation handling */
@@ -204,7 +246,7 @@ InstrAllocTrigger(int n, int instrument_options)
 	int			i;
 
 	for (i = 0; i < n; i++)
-		InstrInit(&tginstr[i].instr, instrument_options);
+		InstrInitOptions(&tginstr[i].instr, instrument_options);
 
 	return tginstr;
 }
@@ -212,13 +254,13 @@ InstrAllocTrigger(int n, int instrument_options)
 void
 InstrStartTrigger(TriggerInstrumentation *tginstr)
 {
-	InstrStartNode(&tginstr->instr);
+	InstrStart(&tginstr->instr);
 }
 
 void
 InstrStopTrigger(TriggerInstrumentation *tginstr, int firings)
 {
-	InstrStopNode(&tginstr->instr, 0);
+	InstrStop(&tginstr->instr);
 	tginstr->firings += firings;
 }
 
diff --git a/src/include/executor/instrument.h b/src/include/executor/instrument.h
index a9c2233227f..b11d64633b5 100644
--- a/src/include/executor/instrument.h
+++ b/src/include/executor/instrument.h
@@ -67,38 +67,55 @@ 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 node creation: */
+	/* 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;
+
+/*
+ * Specialized instrumentation for per-node execution statistics
+ */
+typedef struct NodeInstrumentation
+{
+	Instrumentation instr;
+	/* Parameters set at node creation: */
 	bool		async_mode;		/* true if node is in async mode */
 	/* Info about current plan cycle: */
 	bool		running;		/* true if we've completed first tuple */
-	instr_time	starttime;		/* start time of current iteration of node */
 	instr_time	counter;		/* accumulated runtime for this node */
 	instr_time	firsttuple;		/* time for first tuple of this cycle */
 	double		tuplecount;		/* # of tuples emitted so far this cycle */
-	BufferUsage bufusage_start; /* buffer usage at start */
-	WalUsage	walusage_start; /* WAL usage at start */
 	/* Accumulated statistics across all completed cycles: */
 	instr_time	startup;		/* total startup time */
-	instr_time	total;			/* total time */
 	double		ntuples;		/* total tuples produced */
 	double		ntuples2;		/* secondary node-specific tuple counter */
 	double		nloops;			/* # of run cycles for this node */
 	double		nfiltered1;		/* # of tuples removed by scanqual or joinqual */
 	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;
 
 typedef struct TriggerInstrumentation
 {
@@ -110,14 +127,19 @@ typedef struct TriggerInstrumentation
 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 InstrInitOptions(Instrumentation *instr, int instrument_options);
+extern void InstrStart(Instrumentation *instr);
+extern void InstrStop(Instrumentation *instr);
+
+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 TriggerInstrumentation *InstrAllocTrigger(int n, int instrument_options);
 extern void InstrStartTrigger(TriggerInstrumentation *tginstr);
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index a43bd428a91..605c7a6cc39 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -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 6e78674e282..e05a1e52db4 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1786,6 +1786,7 @@ NextSampleBlock_function
 NextSampleTuple_function
 NextValueExpr
 Node
+NodeInstrumentation
 NodeTag
 NonEmptyRange
 NoneCompressorState
@@ -3384,9 +3385,9 @@ WorkTableScan
 WorkTableScanState
 WorkerInfo
 WorkerInfoData
-WorkerInstrumentation
 WorkerJobDumpPtrType
 WorkerJobRestorePtrType
+WorkerNodeInstrumentation
 Working_State
 WriteBufPtrType
 WriteBytePtrType
-- 
2.47.1