Show Parallel Bitmap Heap Scan worker stats in EXPLAIN ANALYZE

Nodes like Memoize report the cache stats for each parallel worker, so it
makes sense to show the exact and lossy pages in Parallel Bitmap Heap Scan
in a similar way.  Likewise, Sort shows the method and memory used for
each worker.

There was some discussion on whether the leader stats should include the
totals for each parallel worker or not.  I did some analysis on this to
see what other parallel node types do and it seems only Parallel Hash does
anything like this.  All the rest, per what's supported by
ExecParallelRetrieveInstrumentation() are consistent with each other.

Author: David Geier <geidav.pg@gmail.com>
Author: Heikki Linnakangas <hlinnaka@iki.fi>
Author: Donghang Lin <donghanglin@gmail.com>
Author: Alena Rybakina <lena.ribackina@yandex.ru>
Author: David Rowley <dgrowleyml@gmail.com>
Reviewed-by: Dmitry Dolgov <9erthalion6@gmail.com>
Reviewed-by: Michael Christofides <michael@pgmustard.com>
Reviewed-by: Robert Haas <robertmhaas@gmail.com>
Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com>
Reviewed-by: Tomas Vondra <tomas.vondra@enterprisedb.com>
Reviewed-by: Melanie Plageman <melanieplageman@gmail.com>
Reviewed-by: Donghang Lin <donghanglin@gmail.com>
Reviewed-by: Masahiro Ikeda <Masahiro.Ikeda@nttdata.com>
Discussion: https://postgr.es/m/b3d80961-c2e5-38cc-6a32-61886cdf766d%40gmail.com

src/backend/commands/explain.c

@@ -2010,8 +2010,7 @@ ExplainNode(PlanState *planstate, List *ancestors,
 			if (plan->qual)
 				show_instrumentation_count("Rows Removed by Filter", 1,
 										   planstate, es);
-			if (es->analyze)
+			show_tidbitmap_info((BitmapHeapScanState *) planstate, es);
-				show_tidbitmap_info((BitmapHeapScanState *) planstate, es);
 			break;
 		case T_SampleScan:
 			show_tablesample(((SampleScan *) plan)->tablesample,
@@ -3628,31 +3627,70 @@ show_hashagg_info(AggState *aggstate, ExplainState *es)
 }
 
 /*
- * If it's EXPLAIN ANALYZE, show exact/lossy pages for a BitmapHeapScan node
+ * Show exact/lossy pages for a BitmapHeapScan node
  */
 static void
 show_tidbitmap_info(BitmapHeapScanState *planstate, ExplainState *es)
 {
+	if (!es->analyze)
+		return;
+
 	if (es->format != EXPLAIN_FORMAT_TEXT)
 	{
 		ExplainPropertyUInteger("Exact Heap Blocks", NULL,
-								planstate->exact_pages, es);
+								planstate->stats.exact_pages, es);
 		ExplainPropertyUInteger("Lossy Heap Blocks", NULL,
-								planstate->lossy_pages, es);
+								planstate->stats.lossy_pages, es);
 	}
 	else
 	{
-		if (planstate->exact_pages > 0 || planstate->lossy_pages > 0)
+		if (planstate->stats.exact_pages > 0 || planstate->stats.lossy_pages > 0)
 		{
 			ExplainIndentText(es);
 			appendStringInfoString(es->str, "Heap Blocks:");
-			if (planstate->exact_pages > 0)
+			if (planstate->stats.exact_pages > 0)
-				appendStringInfo(es->str, " exact=" UINT64_FORMAT, planstate->exact_pages);
+				appendStringInfo(es->str, " exact=" UINT64_FORMAT, planstate->stats.exact_pages);
-			if (planstate->lossy_pages > 0)
+			if (planstate->stats.lossy_pages > 0)
-				appendStringInfo(es->str, " lossy=" UINT64_FORMAT, planstate->lossy_pages);
+				appendStringInfo(es->str, " lossy=" UINT64_FORMAT, planstate->stats.lossy_pages);
 			appendStringInfoChar(es->str, '\n');
 		}
 	}
+
+	/* Display stats for each parallel worker */
+	if (planstate->pstate != NULL)
+	{
+		for (int n = 0; n < planstate->sinstrument->num_workers; n++)
+		{
+			BitmapHeapScanInstrumentation *si = &planstate->sinstrument->sinstrument[n];
+
+			if (si->exact_pages == 0 && si->lossy_pages == 0)
+				continue;
+
+			if (es->workers_state)
+				ExplainOpenWorker(n, es);
+
+			if (es->format == EXPLAIN_FORMAT_TEXT)
+			{
+				ExplainIndentText(es);
+				appendStringInfoString(es->str, "Heap Blocks:");
+				if (si->exact_pages > 0)
+					appendStringInfo(es->str, " exact=" UINT64_FORMAT, si->exact_pages);
+				if (si->lossy_pages > 0)
+					appendStringInfo(es->str, " lossy=" UINT64_FORMAT, si->lossy_pages);
+				appendStringInfoChar(es->str, '\n');
+			}
+			else
+			{
+				ExplainPropertyUInteger("Exact Heap Blocks", NULL,
+										si->exact_pages, es);
+				ExplainPropertyUInteger("Lossy Heap Blocks", NULL,
+										si->lossy_pages, es);
+			}
+
+			if (es->workers_state)
+				ExplainCloseWorker(n, es);
+		}
+	}
 }
 
 /*

src/backend/executor/execParallel.c

@@ -1076,6 +1076,9 @@ ExecParallelRetrieveInstrumentation(PlanState *planstate,
 		case T_MemoizeState:
 			ExecMemoizeRetrieveInstrumentation((MemoizeState *) planstate);
 			break;
+		case T_BitmapHeapScanState:
+			ExecBitmapHeapRetrieveInstrumentation((BitmapHeapScanState *) planstate);
+			break;
 		default:
 			break;
 	}

src/backend/executor/nodeBitmapHeapscan.c

@@ -236,9 +236,9 @@ BitmapHeapNext(BitmapHeapScanState *node)
 			valid_block = table_scan_bitmap_next_block(scan, tbmres);
 
 			if (tbmres->ntuples >= 0)
-				node->exact_pages++;
+				node->stats.exact_pages++;
 			else
-				node->lossy_pages++;
+				node->stats.lossy_pages++;
 
 			if (!valid_block)
 			{
@@ -627,6 +627,29 @@ ExecEndBitmapHeapScan(BitmapHeapScanState *node)
 {
 	TableScanDesc 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->sinstrument != NULL && IsParallelWorker())
+	{
+		BitmapHeapScanInstrumentation *si;
+
+		Assert(ParallelWorkerNumber <= node->sinstrument->num_workers);
+		si = &node->sinstrument->sinstrument[ParallelWorkerNumber];
+
+		/*
+		 * Here we accumulate the stats rather than performing memcpy on
+		 * node->stats into si.  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 BitmapHeapScanState and
+		 * zeroed stats.
+		 */
+		si->exact_pages += node->stats.exact_pages;
+		si->lossy_pages += node->stats.lossy_pages;
+	}
+
 	/*
 	 * extract information from the node
 	 */
@@ -694,8 +717,10 @@ ExecInitBitmapHeapScan(BitmapHeapScan *node, EState *estate, int eflags)
 	scanstate->tbmiterator = NULL;
 	scanstate->tbmres = NULL;
 	scanstate->pvmbuffer = InvalidBuffer;
-	scanstate->exact_pages = 0;
+
-	scanstate->lossy_pages = 0;
+	/* Zero the statistics counters */
+	memset(&scanstate->stats, 0, sizeof(BitmapHeapScanInstrumentation));
+
 	scanstate->prefetch_iterator = NULL;
 	scanstate->prefetch_pages = 0;
 	scanstate->prefetch_target = 0;
@@ -803,7 +828,18 @@ void
 ExecBitmapHeapEstimate(BitmapHeapScanState *node,
 					   ParallelContext *pcxt)
 {
-	shm_toc_estimate_chunk(&pcxt->estimator, sizeof(ParallelBitmapHeapState));
+	Size		size;
+
+	size = MAXALIGN(sizeof(ParallelBitmapHeapState));
+
+	/* account for instrumentation, if required */
+	if (node->ss.ps.instrument && pcxt->nworkers > 0)
+	{
+		size = add_size(size, offsetof(SharedBitmapHeapInstrumentation, sinstrument));
+		size = add_size(size, mul_size(pcxt->nworkers, sizeof(BitmapHeapScanInstrumentation)));
+	}
+
+	shm_toc_estimate_chunk(&pcxt->estimator, size);
 	shm_toc_estimate_keys(&pcxt->estimator, 1);
 }
 
@@ -818,13 +854,27 @@ ExecBitmapHeapInitializeDSM(BitmapHeapScanState *node,
 							ParallelContext *pcxt)
 {
 	ParallelBitmapHeapState *pstate;
+	SharedBitmapHeapInstrumentation *sinstrument = NULL;
 	dsa_area   *dsa = node->ss.ps.state->es_query_dsa;
+	char	   *ptr;
+	Size		size;
 
 	/* If there's no DSA, there are no workers; initialize nothing. */
 	if (dsa == NULL)
 		return;
 
-	pstate = shm_toc_allocate(pcxt->toc, sizeof(ParallelBitmapHeapState));
+	size = MAXALIGN(sizeof(ParallelBitmapHeapState));
+	if (node->ss.ps.instrument && pcxt->nworkers > 0)
+	{
+		size = add_size(size, offsetof(SharedBitmapHeapInstrumentation, sinstrument));
+		size = add_size(size, mul_size(pcxt->nworkers, sizeof(BitmapHeapScanInstrumentation)));
+	}
+
+	ptr = shm_toc_allocate(pcxt->toc, size);
+	pstate = (ParallelBitmapHeapState *) ptr;
+	ptr += MAXALIGN(sizeof(ParallelBitmapHeapState));
+	if (node->ss.ps.instrument && pcxt->nworkers > 0)
+		sinstrument = (SharedBitmapHeapInstrumentation *) ptr;
 
 	pstate->tbmiterator = 0;
 	pstate->prefetch_iterator = 0;
@@ -837,8 +887,18 @@ ExecBitmapHeapInitializeDSM(BitmapHeapScanState *node,
 
 	ConditionVariableInit(&pstate->cv);
 
+	if (sinstrument)
+	{
+		sinstrument->num_workers = pcxt->nworkers;
+
+		/* ensure any unfilled slots will contain zeroes */
+		memset(sinstrument->sinstrument, 0,
+			   pcxt->nworkers * sizeof(BitmapHeapScanInstrumentation));
+	}
+
 	shm_toc_insert(pcxt->toc, node->ss.ps.plan->plan_node_id, pstate);
 	node->pstate = pstate;
+	node->sinstrument = sinstrument;
 }
 
 /* ----------------------------------------------------------------
@@ -880,10 +940,37 @@ void
 ExecBitmapHeapInitializeWorker(BitmapHeapScanState *node,
 							   ParallelWorkerContext *pwcxt)
 {
-	ParallelBitmapHeapState *pstate;
+	char	   *ptr;
 
 	Assert(node->ss.ps.state->es_query_dsa != NULL);
 
-	pstate = shm_toc_lookup(pwcxt->toc, node->ss.ps.plan->plan_node_id, false);
+	ptr = shm_toc_lookup(pwcxt->toc, node->ss.ps.plan->plan_node_id, false);
-	node->pstate = pstate;
+
+	node->pstate = (ParallelBitmapHeapState *) ptr;
+	ptr += MAXALIGN(sizeof(ParallelBitmapHeapState));
+
+	if (node->ss.ps.instrument)
+		node->sinstrument = (SharedBitmapHeapInstrumentation *) ptr;
+}
+
+/* ----------------------------------------------------------------
+ *		ExecBitmapHeapRetrieveInstrumentation
+ *
+ *		Transfer bitmap heap scan statistics from DSM to private memory.
+ * ----------------------------------------------------------------
+ */
+void
+ExecBitmapHeapRetrieveInstrumentation(BitmapHeapScanState *node)
+{
+	SharedBitmapHeapInstrumentation *sinstrument = node->sinstrument;
+	Size		size;
+
+	if (sinstrument == NULL)
+		return;
+
+	size = offsetof(SharedBitmapHeapInstrumentation, sinstrument)
+		+ sinstrument->num_workers * sizeof(BitmapHeapScanInstrumentation);
+
+	node->sinstrument = palloc(size);
+	memcpy(node->sinstrument, sinstrument, size);
 }

src/include/executor/nodeBitmapHeapscan.h

@@ -28,5 +28,6 @@ extern void ExecBitmapHeapReInitializeDSM(BitmapHeapScanState *node,
 										  ParallelContext *pcxt);
 extern void ExecBitmapHeapInitializeWorker(BitmapHeapScanState *node,
 										   ParallelWorkerContext *pwcxt);
+extern void ExecBitmapHeapRetrieveInstrumentation(BitmapHeapScanState *node);
 
 #endif							/* NODEBITMAPHEAPSCAN_H */

src/include/nodes/execnodes.h

@@ -1746,6 +1746,19 @@ typedef struct BitmapIndexScanState
 	struct IndexScanDescData *biss_ScanDesc;
 } BitmapIndexScanState;
 
+/* ----------------
+ *	 BitmapHeapScanInstrumentation information
+ *
+ *		exact_pages		   total number of exact pages retrieved
+ *		lossy_pages		   total number of lossy pages retrieved
+ * ----------------
+ */
+typedef struct BitmapHeapScanInstrumentation
+{
+	uint64		exact_pages;
+	uint64		lossy_pages;
+} BitmapHeapScanInstrumentation;
+
 /* ----------------
  *	 SharedBitmapState information
  *
@@ -1789,6 +1802,20 @@ typedef struct ParallelBitmapHeapState
 	ConditionVariable cv;
 } ParallelBitmapHeapState;
 
+/* ----------------
+ *	 Instrumentation data for a parallel bitmap heap scan.
+ *
+ * A shared memory struct that each parallel worker copies its
+ * BitmapHeapScanInstrumentation information into at executor shutdown to
+ * allow the leader to display the information in EXPLAIN ANALYZE.
+ * ----------------
+ */
+typedef struct SharedBitmapHeapInstrumentation
+{
+	int			num_workers;
+	BitmapHeapScanInstrumentation sinstrument[FLEXIBLE_ARRAY_MEMBER];
+} SharedBitmapHeapInstrumentation;
+
 /* ----------------
  *	 BitmapHeapScanState information
  *
@@ -1797,8 +1824,7 @@ typedef struct ParallelBitmapHeapState
  *		tbmiterator		   iterator for scanning current pages
  *		tbmres			   current-page data
  *		pvmbuffer		   buffer for visibility-map lookups of prefetched pages
- *		exact_pages		   total number of exact pages retrieved
+ *		stats			   execution statistics
- *		lossy_pages		   total number of lossy pages retrieved
  *		prefetch_iterator  iterator for prefetching ahead of current page
  *		prefetch_pages	   # pages prefetch iterator is ahead of current
  *		prefetch_target    current target prefetch distance
@@ -1807,6 +1833,7 @@ typedef struct ParallelBitmapHeapState
  *		shared_tbmiterator	   shared iterator
  *		shared_prefetch_iterator shared iterator for prefetching
  *		pstate			   shared state for parallel bitmap scan
+ *		sinstrument		   statistics for parallel workers
  * ----------------
  */
 typedef struct BitmapHeapScanState
@@ -1817,8 +1844,7 @@ typedef struct BitmapHeapScanState
 	TBMIterator *tbmiterator;
 	TBMIterateResult *tbmres;
 	Buffer		pvmbuffer;
-	uint64		exact_pages;
+	BitmapHeapScanInstrumentation stats;
-	uint64		lossy_pages;
 	TBMIterator *prefetch_iterator;
 	int			prefetch_pages;
 	int			prefetch_target;
@@ -1827,6 +1853,7 @@ typedef struct BitmapHeapScanState
 	TBMSharedIterator *shared_tbmiterator;
 	TBMSharedIterator *shared_prefetch_iterator;
 	ParallelBitmapHeapState *pstate;
+	SharedBitmapHeapInstrumentation *sinstrument;
 } BitmapHeapScanState;
 
 /* ----------------

src/tools/pgindent/typedefs.list

@@ -262,6 +262,7 @@ BitmapAndPath
 BitmapAndState
 BitmapHeapPath
 BitmapHeapScan
+BitmapHeapScanInstrumentation
 BitmapHeapScanState
 BitmapIndexScan
 BitmapIndexScanState
@@ -2603,6 +2604,7 @@ SetToDefault
 SetupWorkerPtrType
 ShDependObjectInfo
 SharedAggInfo
+SharedBitmapHeapInstrumentation
 SharedBitmapState
 SharedDependencyObjectType
 SharedDependencyType