Allow parallel create index to accumulate buffer usage stats.

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
index dab41ea298aa334463d5a64b7d8cdf46adef292d..61e00b54d03d233c339f0ad228e25180046b6f2c 100644 (file)
--- a/src/backend/access/nbtree/nbtsort.c
+++ b/src/backend/access/nbtree/nbtsort.c
@@ -64,6 +64,7 @@
 #include "access/xlog.h"
 #include "access/xloginsert.h"
 #include "catalog/index.h"
+#include "executor/instrument.h"
 #include "miscadmin.h"
 #include "pgstat.h"
 #include "storage/smgr.h"
@@ -78,6 +79,7 @@
 #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
@@ -192,6 +194,7 @@ typedef struct BTLeader
    Sharedsort *sharedsort;
    Sharedsort *sharedsort2;
    Snapshot    snapshot;
+   BufferUsage *bufferusage;
 } BTLeader;
 
 /*
@@ -1240,6 +1243,7 @@ _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;
@@ -1292,6 +1296,17 @@ _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);
@@ -1361,6 +1376,11 @@ _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;
@@ -1371,6 +1391,7 @@ _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)
@@ -1399,8 +1420,18 @@ _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);
@@ -1537,6 +1568,7 @@ _bt_parallel_build_main(dsm_segment *seg, shm_toc *toc)
    Relation    indexRel;
    LOCKMODE    heapLockmode;
    LOCKMODE    indexLockmode;
+   BufferUsage *bufferusage;
    int         sortmem;
 
 #ifdef BTREE_BUILD_STATS
@@ -1598,11 +1630,18 @@ _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);
 
+   /* 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)
    {