Allow parallel create index to accumulate buffer usage stats.

Amit Kapila · Amit Kapila · commit 13823ad3b012 · 2020-04-09T09:21:09.000+05:30
Currently, we don't account for buffer usage incurred by parallel workers for parallel create index. This commit allows each worker to record the buffer usage stats and leader backend to accumulate that stats at the end of the operation. This will allow pg_stat_statements to display correct buffer usage stats for (parallel) create index command. Reported-by: Julien Rouhaud Author: Sawada Masahiko Reviewed-by: Dilip Kumar, Julien Rouhaud and Amit Kapila Backpatch-through: 11, where this was introduced Discussion: https://postgr.es/m/20200328151721.GB12854@nol
diff --git a/src/backend/access/nbtree/nbtsort.c b/src/backend/access/nbtree/nbtsort.c
@@ -67,6 +67,7 @@
 #include "access/xloginsert.h"
 #include "catalog/index.h"
 #include "commands/progress.h"
+#include "executor/instrument.h"
 #include "miscadmin.h"
 #include "pgstat.h"
 #include "storage/smgr.h"
@@ -81,6 +82,7 @@
 #define PARALLEL_KEY_TUPLESORT			UINT64CONST(0xA000000000000002)
 #define PARALLEL_KEY_TUPLESORT_SPOOL2	UINT64CONST(0xA000000000000003)
 #define PARALLEL_KEY_QUERY_TEXT			UINT64CONST(0xA000000000000004)
+#define PARALLEL_KEY_BUFFER_USAGE		UINT64CONST(0xA000000000000005)
 
 /*
  * DISABLE_LEADER_PARTICIPATION disables the leader's participation in
@@ -203,6 +205,7 @@ typedef struct BTLeader
 	Sharedsort *sharedsort;
 	Sharedsort *sharedsort2;
 	Snapshot	snapshot;
+	BufferUsage *bufferusage;
 } BTLeader;
 
 /*
@@ -1336,6 +1339,7 @@ _bt_begin_parallel(BTBuildState *buildstate, bool isconcurrent, int request)
 	Sharedsort *sharedsort2;
 	BTSpool    *btspool = buildstate->spool;
 	BTLeader   *btleader = (BTLeader *) palloc0(sizeof(BTLeader));
+	BufferUsage *bufferusage;
 	bool		leaderparticipates = true;
 	char	   *sharedquery;
 	int			querylen;
@@ -1388,6 +1392,17 @@ _bt_begin_parallel(BTBuildState *buildstate, bool isconcurrent, int request)
 		shm_toc_estimate_keys(&pcxt->estimator, 3);
 	}
 
+	/*
+	 * Estimate space for BufferUsage -- PARALLEL_KEY_BUFFER_USAGE.
+	 *
+	 * If there are no extensions loaded that care, we could skip this.  We
+	 * have no way of knowing whether anyone's looking at pgBufferUsage, so do
+	 * it unconditionally.
+	 */
+	shm_toc_estimate_chunk(&pcxt->estimator,
+						   mul_size(sizeof(BufferUsage), pcxt->nworkers));
+	shm_toc_estimate_keys(&pcxt->estimator, 1);
+
 	/* Finally, estimate PARALLEL_KEY_QUERY_TEXT space */
 	querylen = strlen(debug_query_string);
 	shm_toc_estimate_chunk(&pcxt->estimator, querylen + 1);
@@ -1459,6 +1474,11 @@ _bt_begin_parallel(BTBuildState *buildstate, bool isconcurrent, int request)
 	memcpy(sharedquery, debug_query_string, querylen + 1);
 	shm_toc_insert(pcxt->toc, PARALLEL_KEY_QUERY_TEXT, sharedquery);
 
+	/* Allocate space for each worker's BufferUsage; no need to initialize */
+	bufferusage = shm_toc_allocate(pcxt->toc,
+								   mul_size(sizeof(BufferUsage), pcxt->nworkers));
+	shm_toc_insert(pcxt->toc, PARALLEL_KEY_BUFFER_USAGE, bufferusage);
+
 	/* Launch workers, saving status for leader/caller */
 	LaunchParallelWorkers(pcxt);
 	btleader->pcxt = pcxt;
@@ -1469,6 +1489,7 @@ _bt_begin_parallel(BTBuildState *buildstate, bool isconcurrent, int request)
 	btleader->sharedsort = sharedsort;
 	btleader->sharedsort2 = sharedsort2;
 	btleader->snapshot = snapshot;
+	btleader->bufferusage = bufferusage;
 
 	/* If no workers were successfully launched, back out (do serial build) */
 	if (pcxt->nworkers_launched == 0)
@@ -1497,8 +1518,18 @@ _bt_begin_parallel(BTBuildState *buildstate, bool isconcurrent, int request)
 static void
 _bt_end_parallel(BTLeader *btleader)
 {
+	int			i;
+
 	/* Shutdown worker processes */
 	WaitForParallelWorkersToFinish(btleader->pcxt);
+
+	/*
+	 * Next, accumulate buffer usage.  (This must wait for the workers to
+	 * finish, or we might get incomplete data.)
+	 */
+	for (i = 0; i < btleader->pcxt->nworkers_launched; i++)
+		InstrAccumParallelQuery(&btleader->bufferusage[i]);
+
 	/* Free last reference to MVCC snapshot, if one was used */
 	if (IsMVCCSnapshot(btleader->snapshot))
 		UnregisterSnapshot(btleader->snapshot);
@@ -1629,6 +1660,7 @@ _bt_parallel_build_main(dsm_segment *seg, shm_toc *toc)
 	Relation	indexRel;
 	LOCKMODE	heapLockmode;
 	LOCKMODE	indexLockmode;
+	BufferUsage *bufferusage;
 	int			sortmem;
 
 #ifdef BTREE_BUILD_STATS
@@ -1690,11 +1722,18 @@ _bt_parallel_build_main(dsm_segment *seg, shm_toc *toc)
 		tuplesort_attach_shared(sharedsort2, seg);
 	}
 
+	/* Prepare to track buffer usage during parallel execution */
+	InstrStartParallelQuery();
+
 	/* Perform sorting of spool, and possibly a spool2 */
 	sortmem = maintenance_work_mem / btshared->scantuplesortstates;
 	_bt_parallel_scan_and_sort(btspool, btspool2, btshared, sharedsort,
 							   sharedsort2, sortmem, false);
 
+	/* Report buffer usage during parallel execution */
+	bufferusage = shm_toc_lookup(toc, PARALLEL_KEY_BUFFER_USAGE, false);
+	InstrEndParallelQuery(&bufferusage[ParallelWorkerNumber]);
+
 #ifdef BTREE_BUILD_STATS
 	if (log_btree_build_stats)
 	{
