Show index search count in EXPLAIN ANALYZE, take 2.

Expose the count of index searches/index descents in EXPLAIN ANALYZE's
output for index scan/index-only scan/bitmap index scan nodes.  This
information is particularly useful with scans that use ScalarArrayOp
quals, where the number of index searches can be unpredictable due to
implementation details that interact with physical index characteristics
(at least with nbtree SAOP scans, since Postgres 17 commit 5bf748b8).
The information shown also provides useful context when EXPLAIN ANALYZE
runs a plan with an index scan node that successfully applied the skip
scan optimization (set to be added to nbtree by an upcoming patch).

The instrumentation works by teaching all index AMs to increment a new
nsearches counter whenever a new index search begins.  The counter is
incremented at exactly the same point that index AMs already increment
the pg_stat_*_indexes.idx_scan counter (we're counting the same event,
but at the scan level rather than the relation level).  Parallel queries
have workers copy their local counter struct into shared memory when an
index scan node ends -- even when it isn't a parallel aware scan node.
An earlier version of this patch that only worked with parallel aware
scans became commit 5ead85fb (though that was quickly reverted by commit
d00107cd following "debug_parallel_query=regress" buildfarm failures).

Our approach doesn't match the approach used when tracking other index
scan related costs (e.g., "Rows Removed by Filter:").  It is comparable
to the approach used in similar cases involving costs that are only
readily accessible inside an access method, not from the executor proper
(e.g., "Heap Blocks:" output for a Bitmap Heap Scan, which was recently
enhanced to show per-worker costs by commit 5a1e6df3, using essentially
the same scheme as the one used here).  It is necessary for index AMs to
have direct responsibility for maintaining the new counter, since the
counter might need to be incremented multiple times per amgettuple call
(or per amgetbitmap call).  But it is also necessary for the executor
proper to manage the shared memory now used to transfer each worker's
counter struct to the leader.

Author: Peter Geoghegan <pg@bowt.ie>
Reviewed-By: Robert Haas <robertmhaas@gmail.com>
Reviewed-By: Tomas Vondra <tomas@vondra.me>
Reviewed-By: Masahiro Ikeda <ikedamsh@oss.nttdata.com>
Reviewed-By: Matthias van de Meent <boekewurm+postgres@gmail.com>
Discussion: https://postgr.es/m/CAH2-WzkRqvaqR2CTNqTZP0z6FuL4-3ED6eQB0yx38XBNj1v-4Q@mail.gmail.com
Discussion: https://postgr.es/m/CAH2-Wz=PKR6rB7qbx+Vnd7eqeB5VTcrW=iJvAsTsKbdG+kW_UA@mail.gmail.com

6 files changed, 348 insertions, 24 deletions

diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 742f3f8c08d..e3fe9b78bb5 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -816,7 +816,7 @@ check_exclusion_or_unique_constraint(Relation heap, Relation index,
 retry:
 	conflict = false;
 	found_self = false;
-	index_scan = index_beginscan(heap, index, &DirtySnapshot, indnkeyatts, 0);
+	index_scan = index_beginscan(heap, index, &DirtySnapshot, NULL, indnkeyatts, 0);
 	index_rescan(index_scan, scankeys, indnkeyatts, NULL, 0);
 
 	while (index_getnext_slot(index_scan, ForwardScanDirection, existing_slot))
diff --git a/src/backend/executor/execParallel.c b/src/backend/executor/execParallel.c
index 1bedb808368..e9337a97d17 100644
--- a/src/backend/executor/execParallel.c
+++ b/src/backend/executor/execParallel.c
@@ -28,6 +28,7 @@
 #include "executor/nodeAgg.h"
 #include "executor/nodeAppend.h"
 #include "executor/nodeBitmapHeapscan.h"
+#include "executor/nodeBitmapIndexscan.h"
 #include "executor/nodeCustom.h"
 #include "executor/nodeForeignscan.h"
 #include "executor/nodeHash.h"
@@ -244,14 +245,19 @@ ExecParallelEstimate(PlanState *planstate, ExecParallelEstimateContext *e)
 									e->pcxt);
 			break;
 		case T_IndexScanState:
-			if (planstate->plan->parallel_aware)
-				ExecIndexScanEstimate((IndexScanState *) planstate,
-									  e->pcxt);
+			/* even when not parallel-aware, for EXPLAIN ANALYZE */
+			ExecIndexScanEstimate((IndexScanState *) planstate,
+								  e->pcxt);
 			break;
 		case T_IndexOnlyScanState:
-			if (planstate->plan->parallel_aware)
-				ExecIndexOnlyScanEstimate((IndexOnlyScanState *) planstate,
-										  e->pcxt);
+			/* even when not parallel-aware, for EXPLAIN ANALYZE */
+			ExecIndexOnlyScanEstimate((IndexOnlyScanState *) planstate,
+									  e->pcxt);
+			break;
+		case T_BitmapIndexScanState:
+			/* even when not parallel-aware, for EXPLAIN ANALYZE */
+			ExecBitmapIndexScanEstimate((BitmapIndexScanState *) planstate,
+										e->pcxt);
 			break;
 		case T_ForeignScanState:
 			if (planstate->plan->parallel_aware)
@@ -468,14 +474,17 @@ ExecParallelInitializeDSM(PlanState *planstate,
 										 d->pcxt);
 			break;
 		case T_IndexScanState:
-			if (planstate->plan->parallel_aware)
-				ExecIndexScanInitializeDSM((IndexScanState *) planstate,
-										   d->pcxt);
+			/* even when not parallel-aware, for EXPLAIN ANALYZE */
+			ExecIndexScanInitializeDSM((IndexScanState *) planstate, d->pcxt);
 			break;
 		case T_IndexOnlyScanState:
-			if (planstate->plan->parallel_aware)
-				ExecIndexOnlyScanInitializeDSM((IndexOnlyScanState *) planstate,
-											   d->pcxt);
+			/* even when not parallel-aware, for EXPLAIN ANALYZE */
+			ExecIndexOnlyScanInitializeDSM((IndexOnlyScanState *) planstate,
+										   d->pcxt);
+			break;
+		case T_BitmapIndexScanState:
+			/* even when not parallel-aware, for EXPLAIN ANALYZE */
+			ExecBitmapIndexScanInitializeDSM((BitmapIndexScanState *) planstate, d->pcxt);
 			break;
 		case T_ForeignScanState:
 			if (planstate->plan->parallel_aware)
@@ -1002,6 +1011,7 @@ ExecParallelReInitializeDSM(PlanState *planstate,
 				ExecHashJoinReInitializeDSM((HashJoinState *) planstate,
 											pcxt);
 			break;
+		case T_BitmapIndexScanState:
 		case T_HashState:
 		case T_SortState:
 		case T_IncrementalSortState:
@@ -1063,6 +1073,15 @@ ExecParallelRetrieveInstrumentation(PlanState *planstate,
 	/* Perform any node-type-specific work that needs to be done. */
 	switch (nodeTag(planstate))
 	{
+		case T_IndexScanState:
+			ExecIndexScanRetrieveInstrumentation((IndexScanState *) planstate);
+			break;
+		case T_IndexOnlyScanState:
+			ExecIndexOnlyScanRetrieveInstrumentation((IndexOnlyScanState *) planstate);
+			break;
+		case T_BitmapIndexScanState:
+			ExecBitmapIndexScanRetrieveInstrumentation((BitmapIndexScanState *) planstate);
+			break;
 		case T_SortState:
 			ExecSortRetrieveInstrumentation((SortState *) planstate);
 			break;
@@ -1330,14 +1349,18 @@ ExecParallelInitializeWorker(PlanState *planstate, ParallelWorkerContext *pwcxt)
 				ExecSeqScanInitializeWorker((SeqScanState *) planstate, pwcxt);
 			break;
 		case T_IndexScanState:
-			if (planstate->plan->parallel_aware)
-				ExecIndexScanInitializeWorker((IndexScanState *) planstate,
-											  pwcxt);
+			/* even when not parallel-aware, for EXPLAIN ANALYZE */
+			ExecIndexScanInitializeWorker((IndexScanState *) planstate, pwcxt);
 			break;
 		case T_IndexOnlyScanState:
-			if (planstate->plan->parallel_aware)
-				ExecIndexOnlyScanInitializeWorker((IndexOnlyScanState *) planstate,
-												  pwcxt);
+			/* even when not parallel-aware, for EXPLAIN ANALYZE */
+			ExecIndexOnlyScanInitializeWorker((IndexOnlyScanState *) planstate,
+											  pwcxt);
+			break;
+		case T_BitmapIndexScanState:
+			/* even when not parallel-aware, for EXPLAIN ANALYZE */
+			ExecBitmapIndexScanInitializeWorker((BitmapIndexScanState *) planstate,
+												pwcxt);
 			break;
 		case T_ForeignScanState:
 			if (planstate->plan->parallel_aware)
diff --git a/src/backend/executor/execReplication.c b/src/backend/executor/execReplication.c
index f59cb9098ff..0a9b880d250 100644
--- a/src/backend/executor/execReplication.c
+++ b/src/backend/executor/execReplication.c
@@ -202,7 +202,7 @@ RelationFindReplTupleByIndex(Relation rel, Oid idxoid,
 	skey_attoff = build_replindex_scan_key(skey, rel, idxrel, searchslot);
 
 	/* Start an index scan. */
-	scan = index_beginscan(rel, idxrel, &snap, skey_attoff, 0);
+	scan = index_beginscan(rel, idxrel, &snap, NULL, skey_attoff, 0);
 
 retry:
 	found = false;
diff --git a/src/backend/executor/nodeBitmapIndexscan.c b/src/backend/executor/nodeBitmapIndexscan.c
index 0b32c3a022f..abbb033881a 100644
--- a/src/backend/executor/nodeBitmapIndexscan.c
+++ b/src/backend/executor/nodeBitmapIndexscan.c
@@ -184,6 +184,27 @@ ExecEndBitmapIndexScan(BitmapIndexScanState *node)
 	indexScanDesc = node->biss_ScanDesc;
 
 	/*
+	 * When ending a parallel worker, copy the statistics gathered by the
+	 * worker back into shared memory so that it can be picked up by the main
+	 * process to report in EXPLAIN ANALYZE
+	 */
+	if (node->biss_SharedInfo != NULL && IsParallelWorker())
+	{
+		IndexScanInstrumentation *winstrument;
+
+		Assert(ParallelWorkerNumber <= node->biss_SharedInfo->num_workers);
+		winstrument = &node->biss_SharedInfo->winstrument[ParallelWorkerNumber];
+
+		/*
+		 * We have to accumulate the stats rather than performing a memcpy.
+		 * When a Gather/GatherMerge node finishes it will perform planner
+		 * shutdown on the workers.  On rescan it will spin up new workers
+		 * which will have a new BitmapIndexScanState and zeroed stats.
+		 */
+		winstrument->nsearches += node->biss_Instrument.nsearches;
+	}
+
+	/*
 	 * close the index relation (no-op if we didn't open it)
 	 */
 	if (indexScanDesc)
@@ -302,6 +323,7 @@ ExecInitBitmapIndexScan(BitmapIndexScan *node, EState *estate, int eflags)
 	indexstate->biss_ScanDesc =
 		index_beginscan_bitmap(indexstate->biss_RelationDesc,
 							   estate->es_snapshot,
+							   &indexstate->biss_Instrument,
 							   indexstate->biss_NumScanKeys);
 
 	/*
@@ -319,3 +341,97 @@ ExecInitBitmapIndexScan(BitmapIndexScan *node, EState *estate, int eflags)
 	 */
 	return indexstate;
 }
+
+/* ----------------------------------------------------------------
+ *		ExecBitmapIndexScanEstimate
+ *
+ *		Compute the amount of space we'll need in the parallel
+ *		query DSM, and inform pcxt->estimator about our needs.
+ * ----------------------------------------------------------------
+ */
+void
+ExecBitmapIndexScanEstimate(BitmapIndexScanState *node, ParallelContext *pcxt)
+{
+	Size		size;
+
+	/*
+	 * Parallel bitmap index scans are not supported, but we still need to
+	 * store the scan's instrumentation in DSM during parallel query
+	 */
+	if (!node->ss.ps.instrument || pcxt->nworkers == 0)
+		return;
+
+	size = offsetof(SharedIndexScanInstrumentation, winstrument) +
+		pcxt->nworkers * sizeof(IndexScanInstrumentation);
+	shm_toc_estimate_chunk(&pcxt->estimator, size);
+	shm_toc_estimate_keys(&pcxt->estimator, 1);
+}
+
+/* ----------------------------------------------------------------
+ *		ExecBitmapIndexScanInitializeDSM
+ *
+ *		Set up bitmap index scan shared instrumentation.
+ * ----------------------------------------------------------------
+ */
+void
+ExecBitmapIndexScanInitializeDSM(BitmapIndexScanState *node,
+								 ParallelContext *pcxt)
+{
+	Size		size;
+
+	/* don't need this if not instrumenting or no workers */
+	if (!node->ss.ps.instrument || pcxt->nworkers == 0)
+		return;
+
+	size = offsetof(SharedIndexScanInstrumentation, winstrument) +
+		pcxt->nworkers * sizeof(IndexScanInstrumentation);
+	node->biss_SharedInfo =
+		(SharedIndexScanInstrumentation *) shm_toc_allocate(pcxt->toc,
+															size);
+	shm_toc_insert(pcxt->toc, node->ss.ps.plan->plan_node_id,
+				   node->biss_SharedInfo);
+
+	/* Each per-worker area must start out as zeroes */
+	memset(node->biss_SharedInfo, 0, size);
+	node->biss_SharedInfo->num_workers = pcxt->nworkers;
+}
+
+/* ----------------------------------------------------------------
+ *		ExecBitmapIndexScanInitializeWorker
+ *
+ *		Copy relevant information from TOC into planstate.
+ * ----------------------------------------------------------------
+ */
+void
+ExecBitmapIndexScanInitializeWorker(BitmapIndexScanState *node,
+									ParallelWorkerContext *pwcxt)
+{
+	/* don't need this if not instrumenting */
+	if (!node->ss.ps.instrument)
+		return;
+
+	node->biss_SharedInfo = (SharedIndexScanInstrumentation *)
+		shm_toc_lookup(pwcxt->toc, node->ss.ps.plan->plan_node_id, false);
+}
+
+/* ----------------------------------------------------------------
+ * ExecBitmapIndexScanRetrieveInstrumentation
+ *
+ *		Transfer bitmap index scan statistics from DSM to private memory.
+ * ----------------------------------------------------------------
+ */
+void
+ExecBitmapIndexScanRetrieveInstrumentation(BitmapIndexScanState *node)
+{
+	SharedIndexScanInstrumentation *SharedInfo = node->biss_SharedInfo;
+	size_t		size;
+
+	if (SharedInfo == NULL)
+		return;
+
+	/* Create a copy of SharedInfo in backend-local memory */
+	size = offsetof(SharedIndexScanInstrumentation, winstrument) +
+		SharedInfo->num_workers * sizeof(IndexScanInstrumentation);
+	node->biss_SharedInfo = palloc(size);
+	memcpy(node->biss_SharedInfo, SharedInfo, size);
+}
diff --git a/src/backend/executor/nodeIndexonlyscan.c b/src/backend/executor/nodeIndexonlyscan.c
index e6635233155..f464cca9507 100644
--- a/src/backend/executor/nodeIndexonlyscan.c
+++ b/src/backend/executor/nodeIndexonlyscan.c
@@ -92,6 +92,7 @@ IndexOnlyNext(IndexOnlyScanState *node)
 		scandesc = index_beginscan(node->ss.ss_currentRelation,
 								   node->ioss_RelationDesc,
 								   estate->es_snapshot,
+								   &node->ioss_Instrument,
 								   node->ioss_NumScanKeys,
 								   node->ioss_NumOrderByKeys);
 
@@ -414,6 +415,27 @@ ExecEndIndexOnlyScan(IndexOnlyScanState *node)
 	}
 
 	/*
+	 * When ending a parallel worker, copy the statistics gathered by the
+	 * worker back into shared memory so that it can be picked up by the main
+	 * process to report in EXPLAIN ANALYZE
+	 */
+	if (node->ioss_SharedInfo != NULL && IsParallelWorker())
+	{
+		IndexScanInstrumentation *winstrument;
+
+		Assert(ParallelWorkerNumber <= node->ioss_SharedInfo->num_workers);
+		winstrument = &node->ioss_SharedInfo->winstrument[ParallelWorkerNumber];
+
+		/*
+		 * We have to accumulate the stats rather than performing a memcpy.
+		 * When a Gather/GatherMerge node finishes it will perform planner
+		 * shutdown on the workers.  On rescan it will spin up new workers
+		 * which will have a new IndexOnlyScanState and zeroed stats.
+		 */
+		winstrument->nsearches += node->ioss_Instrument.nsearches;
+	}
+
+	/*
 	 * close the index relation (no-op if we didn't open it)
 	 */
 	if (indexScanDesc)
@@ -707,11 +729,21 @@ ExecIndexOnlyScanEstimate(IndexOnlyScanState *node,
 						  ParallelContext *pcxt)
 {
 	EState	   *estate = node->ss.ps.state;
+	bool		instrument = (node->ss.ps.instrument != NULL);
+	bool		parallel_aware = node->ss.ps.plan->parallel_aware;
+
+	if (!instrument && !parallel_aware)
+	{
+		/* No DSM required by the scan */
+		return;
+	}
 
 	node->ioss_PscanLen = index_parallelscan_estimate(node->ioss_RelationDesc,
 													  node->ioss_NumScanKeys,
 													  node->ioss_NumOrderByKeys,
-													  estate->es_snapshot);
+													  estate->es_snapshot,
+													  instrument, parallel_aware,
+													  pcxt->nworkers);
 	shm_toc_estimate_chunk(&pcxt->estimator, node->ioss_PscanLen);
 	shm_toc_estimate_keys(&pcxt->estimator, 1);
 }
@@ -728,16 +760,33 @@ ExecIndexOnlyScanInitializeDSM(IndexOnlyScanState *node,
 {
 	EState	   *estate = node->ss.ps.state;
 	ParallelIndexScanDesc piscan;
+	bool		instrument = node->ss.ps.instrument != NULL;
+	bool		parallel_aware = node->ss.ps.plan->parallel_aware;
+
+	if (!instrument && !parallel_aware)
+	{
+		/* No DSM required by the scan */
+		return;
+	}
 
 	piscan = shm_toc_allocate(pcxt->toc, node->ioss_PscanLen);
 	index_parallelscan_initialize(node->ss.ss_currentRelation,
 								  node->ioss_RelationDesc,
 								  estate->es_snapshot,
-								  piscan);
+								  instrument, parallel_aware, pcxt->nworkers,
+								  &node->ioss_SharedInfo, piscan);
 	shm_toc_insert(pcxt->toc, node->ss.ps.plan->plan_node_id, piscan);
+
+	if (!parallel_aware)
+	{
+		/* Only here to initialize SharedInfo in DSM */
+		return;
+	}
+
 	node->ioss_ScanDesc =
 		index_beginscan_parallel(node->ss.ss_currentRelation,
 								 node->ioss_RelationDesc,
+								 &node->ioss_Instrument,
 								 node->ioss_NumScanKeys,
 								 node->ioss_NumOrderByKeys,
 								 piscan);
@@ -764,6 +813,7 @@ void
 ExecIndexOnlyScanReInitializeDSM(IndexOnlyScanState *node,
 								 ParallelContext *pcxt)
 {
+	Assert(node->ss.ps.plan->parallel_aware);
 	index_parallelrescan(node->ioss_ScanDesc);
 }
 
@@ -778,11 +828,31 @@ ExecIndexOnlyScanInitializeWorker(IndexOnlyScanState *node,
 								  ParallelWorkerContext *pwcxt)
 {
 	ParallelIndexScanDesc piscan;
+	bool		instrument = node->ss.ps.instrument != NULL;
+	bool		parallel_aware = node->ss.ps.plan->parallel_aware;
+
+	if (!instrument && !parallel_aware)
+	{
+		/* No DSM required by the scan */
+		return;
+	}
 
 	piscan = shm_toc_lookup(pwcxt->toc, node->ss.ps.plan->plan_node_id, false);
+
+	if (instrument)
+		node->ioss_SharedInfo = (SharedIndexScanInstrumentation *)
+			OffsetToPointer(piscan, piscan->ps_offset_ins);
+
+	if (!parallel_aware)
+	{
+		/* Only here to set up worker node's SharedInfo */
+		return;
+	}
+
 	node->ioss_ScanDesc =
 		index_beginscan_parallel(node->ss.ss_currentRelation,
 								 node->ioss_RelationDesc,
+								 &node->ioss_Instrument,
 								 node->ioss_NumScanKeys,
 								 node->ioss_NumOrderByKeys,
 								 piscan);
@@ -797,3 +867,25 @@ ExecIndexOnlyScanInitializeWorker(IndexOnlyScanState *node,
 					 node->ioss_ScanKeys, node->ioss_NumScanKeys,
 					 node->ioss_OrderByKeys, node->ioss_NumOrderByKeys);
 }
+
+/* ----------------------------------------------------------------
+ *		ExecIndexOnlyScanRetrieveInstrumentation
+ *
+ *		Transfer index-only scan statistics from DSM to private memory.
+ * ----------------------------------------------------------------
+ */
+void
+ExecIndexOnlyScanRetrieveInstrumentation(IndexOnlyScanState *node)
+{
+	SharedIndexScanInstrumentation *SharedInfo = node->ioss_SharedInfo;
+	size_t		size;
+
+	if (SharedInfo == NULL)
+		return;
+
+	/* Create a copy of SharedInfo in backend-local memory */
+	size = offsetof(SharedIndexScanInstrumentation, winstrument) +
+		SharedInfo->num_workers * sizeof(IndexScanInstrumentation);
+	node->ioss_SharedInfo = palloc(size);
+	memcpy(node->ioss_SharedInfo, SharedInfo, size);
+}
diff --git a/src/backend/executor/nodeIndexscan.c b/src/backend/executor/nodeIndexscan.c
index c30b9c2c197..7fcaa37fe62 100644
--- a/src/backend/executor/nodeIndexscan.c
+++ b/src/backend/executor/nodeIndexscan.c
@@ -109,6 +109,7 @@ IndexNext(IndexScanState *node)
 		scandesc = index_beginscan(node->ss.ss_currentRelation,
 								   node->iss_RelationDesc,
 								   estate->es_snapshot,
+								   &node->iss_Instrument,
 								   node->iss_NumScanKeys,
 								   node->iss_NumOrderByKeys);
 
@@ -204,6 +205,7 @@ IndexNextWithReorder(IndexScanState *node)
 		scandesc = index_beginscan(node->ss.ss_currentRelation,
 								   node->iss_RelationDesc,
 								   estate->es_snapshot,
+								   &node->iss_Instrument,
 								   node->iss_NumScanKeys,
 								   node->iss_NumOrderByKeys);
 
@@ -794,6 +796,27 @@ ExecEndIndexScan(IndexScanState *node)
 	indexScanDesc = node->iss_ScanDesc;
 
 	/*
+	 * When ending a parallel worker, copy the statistics gathered by the
+	 * worker back into shared memory so that it can be picked up by the main
+	 * process to report in EXPLAIN ANALYZE
+	 */
+	if (node->iss_SharedInfo != NULL && IsParallelWorker())
+	{
+		IndexScanInstrumentation *winstrument;
+
+		Assert(ParallelWorkerNumber <= node->iss_SharedInfo->num_workers);
+		winstrument = &node->iss_SharedInfo->winstrument[ParallelWorkerNumber];
+
+		/*
+		 * We have to accumulate the stats rather than performing a memcpy.
+		 * When a Gather/GatherMerge node finishes it will perform planner
+		 * shutdown on the workers.  On rescan it will spin up new workers
+		 * which will have a new IndexOnlyScanState and zeroed stats.
+		 */
+		winstrument->nsearches += node->iss_Instrument.nsearches;
+	}
+
+	/*
 	 * close the index relation (no-op if we didn't open it)
 	 */
 	if (indexScanDesc)
@@ -1642,11 +1665,21 @@ ExecIndexScanEstimate(IndexScanState *node,
 					  ParallelContext *pcxt)
 {
 	EState	   *estate = node->ss.ps.state;
+	bool		instrument = node->ss.ps.instrument != NULL;
+	bool		parallel_aware = node->ss.ps.plan->parallel_aware;
+
+	if (!instrument && !parallel_aware)
+	{
+		/* No DSM required by the scan */
+		return;
+	}
 
 	node->iss_PscanLen = index_parallelscan_estimate(node->iss_RelationDesc,
 													 node->iss_NumScanKeys,
 													 node->iss_NumOrderByKeys,
-													 estate->es_snapshot);
+													 estate->es_snapshot,
+													 instrument, parallel_aware,
+													 pcxt->nworkers);
 	shm_toc_estimate_chunk(&pcxt->estimator, node->iss_PscanLen);
 	shm_toc_estimate_keys(&pcxt->estimator, 1);
 }
@@ -1663,16 +1696,33 @@ ExecIndexScanInitializeDSM(IndexScanState *node,
 {
 	EState	   *estate = node->ss.ps.state;
 	ParallelIndexScanDesc piscan;
+	bool		instrument = node->ss.ps.instrument != NULL;
+	bool		parallel_aware = node->ss.ps.plan->parallel_aware;
+
+	if (!instrument && !parallel_aware)
+	{
+		/* No DSM required by the scan */
+		return;
+	}
 
 	piscan = shm_toc_allocate(pcxt->toc, node->iss_PscanLen);
 	index_parallelscan_initialize(node->ss.ss_currentRelation,
 								  node->iss_RelationDesc,
 								  estate->es_snapshot,
-								  piscan);
+								  instrument, parallel_aware, pcxt->nworkers,
+								  &node->iss_SharedInfo, piscan);
 	shm_toc_insert(pcxt->toc, node->ss.ps.plan->plan_node_id, piscan);
+
+	if (!parallel_aware)
+	{
+		/* Only here to initialize SharedInfo in DSM */
+		return;
+	}
+
 	node->iss_ScanDesc =
 		index_beginscan_parallel(node->ss.ss_currentRelation,
 								 node->iss_RelationDesc,
+								 &node->iss_Instrument,
 								 node->iss_NumScanKeys,
 								 node->iss_NumOrderByKeys,
 								 piscan);
@@ -1697,6 +1747,7 @@ void
 ExecIndexScanReInitializeDSM(IndexScanState *node,
 							 ParallelContext *pcxt)
 {
+	Assert(node->ss.ps.plan->parallel_aware);
 	index_parallelrescan(node->iss_ScanDesc);
 }
 
@@ -1711,11 +1762,31 @@ ExecIndexScanInitializeWorker(IndexScanState *node,
 							  ParallelWorkerContext *pwcxt)
 {
 	ParallelIndexScanDesc piscan;
+	bool		instrument = node->ss.ps.instrument != NULL;
+	bool		parallel_aware = node->ss.ps.plan->parallel_aware;
+
+	if (!instrument && !parallel_aware)
+	{
+		/* No DSM required by the scan */
+		return;
+	}
 
 	piscan = shm_toc_lookup(pwcxt->toc, node->ss.ps.plan->plan_node_id, false);
+
+	if (instrument)
+		node->iss_SharedInfo = (SharedIndexScanInstrumentation *)
+			OffsetToPointer(piscan, piscan->ps_offset_ins);
+
+	if (!parallel_aware)
+	{
+		/* Only here to set up worker node's SharedInfo */
+		return;
+	}
+
 	node->iss_ScanDesc =
 		index_beginscan_parallel(node->ss.ss_currentRelation,
 								 node->iss_RelationDesc,
+								 &node->iss_Instrument,
 								 node->iss_NumScanKeys,
 								 node->iss_NumOrderByKeys,
 								 piscan);
@@ -1729,3 +1800,25 @@ ExecIndexScanInitializeWorker(IndexScanState *node,
 					 node->iss_ScanKeys, node->iss_NumScanKeys,
 					 node->iss_OrderByKeys, node->iss_NumOrderByKeys);
 }
+
+/* ----------------------------------------------------------------
+ * ExecIndexScanRetrieveInstrumentation
+ *
+ *		Transfer index scan statistics from DSM to private memory.
+ * ----------------------------------------------------------------
+ */
+void
+ExecIndexScanRetrieveInstrumentation(IndexScanState *node)
+{
+	SharedIndexScanInstrumentation *SharedInfo = node->iss_SharedInfo;
+	size_t		size;
+
+	if (SharedInfo == NULL)
+		return;
+
+	/* Create a copy of SharedInfo in backend-local memory */
+	size = offsetof(SharedIndexScanInstrumentation, winstrument) +
+		SharedInfo->num_workers * sizeof(IndexScanInstrumentation);
+	node->iss_SharedInfo = palloc(size);
+	memcpy(node->iss_SharedInfo, SharedInfo, size);
+}