From aac60985d6bc70bfedf77a77ee3c512da87bfcb1 Mon Sep 17 00:00:00 2001 From: Melanie Plageman Date: Tue, 13 Feb 2024 14:27:57 -0500 Subject: [PATCH v1 11/11] BitmapHeapScan uses streaming read API Remove all of the code to do prefetching from BitmapHeapScan code and rely on the streaming read API prefetching. Heap table AM implements a streaming read callback which uses the iterator to get the next valid block that needs to be fetched for the streaming read API. --- src/backend/access/gin/ginget.c | 15 +- src/backend/access/gin/ginscan.c | 7 + src/backend/access/heap/heapam.c | 71 +++++ src/backend/access/heap/heapam_handler.c | 78 +++-- src/backend/executor/nodeBitmapHeapscan.c | 328 +--------------------- src/backend/nodes/tidbitmap.c | 80 +++--- src/include/access/heapam.h | 2 + src/include/access/tableam.h | 14 +- src/include/nodes/execnodes.h | 19 -- src/include/nodes/tidbitmap.h | 8 +- 10 files changed, 178 insertions(+), 444 deletions(-) diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c index 0b4f2ebadb6..3ce28078a6f 100644 --- a/src/backend/access/gin/ginget.c +++ b/src/backend/access/gin/ginget.c @@ -373,7 +373,10 @@ restartScanEntry: if (entry->matchBitmap) { if (entry->matchIterator) + { tbm_end_iterate(entry->matchIterator); + pfree(entry->matchResult); + } entry->matchIterator = NULL; tbm_free(entry->matchBitmap); entry->matchBitmap = NULL; @@ -386,6 +389,7 @@ restartScanEntry: if (entry->matchBitmap && !tbm_is_empty(entry->matchBitmap)) { entry->matchIterator = tbm_begin_iterate(entry->matchBitmap); + entry->matchResult = palloc0(TBM_ITERATE_RESULT_SIZE); entry->isFinished = false; } } @@ -823,21 +827,24 @@ entryGetItem(GinState *ginstate, GinScanEntry entry, { /* * If we've exhausted all items on this block, move to next block - * in the bitmap. + * in the bitmap. tbm_iterate() sets matchResult->blockno to + * InvalidBlockNumber when the bitmap is exhausted. */ - while (entry->matchResult == NULL || + while ((!BlockNumberIsValid(entry->matchResult->blockno)) || (entry->matchResult->ntuples >= 0 && entry->offset >= entry->matchResult->ntuples) || entry->matchResult->blockno < advancePastBlk || (ItemPointerIsLossyPage(&advancePast) && entry->matchResult->blockno == advancePastBlk)) { - entry->matchResult = tbm_iterate(entry->matchIterator); - if (entry->matchResult == NULL) + tbm_iterate(entry->matchIterator, entry->matchResult); + if (!BlockNumberIsValid(entry->matchResult->blockno)) { ItemPointerSetInvalid(&entry->curItem); tbm_end_iterate(entry->matchIterator); + pfree(entry->matchResult); + entry->matchResult = NULL; entry->matchIterator = NULL; entry->isFinished = true; break; diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c index af24d38544e..be27f9fe07e 100644 --- a/src/backend/access/gin/ginscan.c +++ b/src/backend/access/gin/ginscan.c @@ -246,7 +246,14 @@ ginFreeScanKeys(GinScanOpaque so) if (entry->list) pfree(entry->list); if (entry->matchIterator) + { tbm_end_iterate(entry->matchIterator); + if (entry->matchResult) + { + pfree(entry->matchResult); + entry->matchResult = NULL; + } + } if (entry->matchBitmap) tbm_free(entry->matchBitmap); } diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c index d8569373987..86484c6c72a 100644 --- a/src/backend/access/heap/heapam.c +++ b/src/backend/access/heap/heapam.c @@ -115,6 +115,8 @@ static XLogRecPtr log_heap_new_cid(Relation relation, HeapTuple tup); static HeapTuple ExtractReplicaIdentity(Relation relation, HeapTuple tp, bool key_required, bool *copy); +static BlockNumber bitmapheap_pgsr_next_single(PgStreamingRead *pgsr, void *pgsr_private, + void *per_buffer_data); /* * Each tuple lock mode has a corresponding heavyweight lock, and one or two @@ -335,6 +337,22 @@ initscan(HeapScanDesc scan, ScanKey key, bool keep_startblock) if (key != NULL && scan->rs_base.rs_nkeys > 0) memcpy(scan->rs_base.rs_key, key, scan->rs_base.rs_nkeys * sizeof(ScanKeyData)); + if (scan->rs_base.rs_flags & SO_TYPE_BITMAPSCAN) + { + if (scan->pgsr) + pg_streaming_read_free(scan->pgsr); + + scan->pgsr = pg_streaming_read_buffer_alloc(PGSR_FLAG_DEFAULT, + scan, + TBM_ITERATE_RESULT_SIZE, + scan->rs_strategy, + BMR_REL(scan->rs_base.rs_rd), + MAIN_FORKNUM, + bitmapheap_pgsr_next_single); + + + } + /* * Currently, we only have a stats counter for sequential heap scans (but * e.g for bitmap scans the underlying bitmap index scans will be counted, @@ -955,6 +973,7 @@ heap_beginscan(Relation relation, Snapshot snapshot, scan->rs_base.rs_flags = flags; scan->rs_base.rs_parallel = parallel_scan; scan->rs_strategy = NULL; /* set in initscan */ + scan->pgsr = NULL; scan->vmbuffer = InvalidBuffer; scan->empty_tuples = 0; scan->rs_base.lossy_pages = 0; @@ -1113,6 +1132,13 @@ heap_endscan(TableScanDesc sscan) if (scan->rs_base.rs_flags & SO_TEMP_SNAPSHOT) UnregisterSnapshot(scan->rs_base.rs_snapshot); + if (scan->rs_base.rs_flags & SO_TYPE_BITMAPSCAN) + { + if (scan->pgsr) + pg_streaming_read_free(scan->pgsr); + scan->pgsr = NULL; + } + pfree(scan); } @@ -10270,3 +10296,48 @@ HeapCheckForSerializableConflictOut(bool visible, Relation relation, CheckForSerializableConflictOut(relation, xid, snapshot); } + +static BlockNumber +bitmapheap_pgsr_next_single(PgStreamingRead *pgsr, void *pgsr_private, + void *per_buffer_data) +{ + TBMIterateResult *tbmres = per_buffer_data; + HeapScanDesc hdesc = (HeapScanDesc) pgsr_private; + + for (;;) + { + if (hdesc->rs_base.shared_tbmiterator) + tbm_shared_iterate(hdesc->rs_base.shared_tbmiterator, tbmres); + else + tbm_iterate(hdesc->rs_base.tbmiterator, tbmres); + + /* no more entries in the bitmap */ + if (!BlockNumberIsValid(tbmres->blockno)) + return InvalidBlockNumber; + + /* + * Ignore any claimed entries past what we think is the end of the + * relation. It may have been extended after the start of our scan (we + * only hold an AccessShareLock, and it could be inserts from this + * backend). We don't take this optimization in SERIALIZABLE + * isolation though, as we need to examine all invisible tuples + * reachable by the index. + */ + if (!IsolationIsSerializable() && tbmres->blockno >= hdesc->rs_nblocks) + continue; + + + if (hdesc->rs_base.rs_flags & SO_CAN_SKIP_FETCH && + !tbmres->recheck && + VM_ALL_VISIBLE(hdesc->rs_base.rs_rd, tbmres->blockno, &hdesc->vmbuffer)) + { + hdesc->empty_tuples += tbmres->ntuples; + continue; + } + + return tbmres->blockno; + } + + /* not reachable */ + Assert(false); +} diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index d55ece23a35..0cd586cd4b8 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -2113,77 +2113,65 @@ heapam_estimate_rel_size(Relation rel, int32 *attr_widths, */ static bool -heapam_scan_bitmap_next_block(TableScanDesc scan, - bool *recheck, BlockNumber *blockno) +heapam_scan_bitmap_next_block(TableScanDesc scan, bool *recheck) { HeapScanDesc hscan = (HeapScanDesc) scan; + void *io_private; BlockNumber block; Buffer buffer; Snapshot snapshot; int ntup; TBMIterateResult *tbmres; + Assert(hscan->pgsr); + hscan->rs_cindex = 0; hscan->rs_ntuples = 0; - *blockno = InvalidBlockNumber; *recheck = true; - do + /* Release buffer containing previous block. */ + if (BufferIsValid(hscan->rs_cbuf)) { - if (scan->shared_tbmiterator) - tbmres = tbm_shared_iterate(scan->shared_tbmiterator); - else - tbmres = tbm_iterate(scan->tbmiterator); + ReleaseBuffer(hscan->rs_cbuf); + hscan->rs_cbuf = InvalidBuffer; + } + + hscan->rs_cbuf = pg_streaming_read_buffer_get_next(hscan->pgsr, &io_private); - if (tbmres == NULL) + if (BufferIsInvalid(hscan->rs_cbuf)) + { + if (BufferIsValid(hscan->vmbuffer)) { - /* no more entries in the bitmap */ - Assert(hscan->empty_tuples == 0); - return false; + ReleaseBuffer(hscan->vmbuffer); + hscan->vmbuffer = InvalidBuffer; } /* - * Ignore any claimed entries past what we think is the end of the - * relation. It may have been extended after the start of our scan (we - * only hold an AccessShareLock, and it could be inserts from this - * backend). We don't take this optimization in SERIALIZABLE - * isolation though, as we need to examine all invisible tuples - * reachable by the index. + * Bitmap is exhausted. Time to emit empty tuples if relevant. We emit + * all empty tuples at the end instead of emitting them per block we + * skip fetching. This is necessary because the streaming read API will + * only return TBMIterateResults for blocks actually fetched. When we + * skip fetching a block, we keep track of how many empty tuples to + * emit at the end of the BitmapHeapScan. We do not recheck all NULL + * tuples. */ - } while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks); + *recheck = false; + return hscan->empty_tuples > 0; + } - /* Got a valid block */ - *blockno = tbmres->blockno; - *recheck = tbmres->recheck; + Assert(io_private); - /* - * We can skip fetching the heap page if we don't need any fields from the - * heap, and the bitmap entries don't need rechecking, and all tuples on - * the page are visible to our transaction. - */ - if (scan->rs_flags & SO_CAN_SKIP_FETCH && - !tbmres->recheck && - VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->vmbuffer)) - { - /* can't be lossy in the skip_fetch case */ - Assert(tbmres->ntuples >= 0); - Assert(hscan->empty_tuples >= 0); + tbmres = (TBMIterateResult *) io_private; - hscan->empty_tuples += tbmres->ntuples; + Assert(BufferGetBlockNumber(hscan->rs_cbuf) == tbmres->blockno); - return true; - } + *recheck = tbmres->recheck; - block = tbmres->blockno; + hscan->rs_cblock = tbmres->blockno; + hscan->rs_ntuples = tbmres->ntuples; - /* - * Acquire pin on the target heap page, trading in any pin we held before. - */ - hscan->rs_cbuf = ReleaseAndReadBuffer(hscan->rs_cbuf, - scan->rs_rd, - block); - hscan->rs_cblock = block; + block = tbmres->blockno; buffer = hscan->rs_cbuf; snapshot = scan->rs_snapshot; diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c index efc6952e353..8b7f87a4779 100644 --- a/src/backend/executor/nodeBitmapHeapscan.c +++ b/src/backend/executor/nodeBitmapHeapscan.c @@ -56,11 +56,6 @@ static TupleTableSlot *BitmapHeapNext(BitmapHeapScanState *node); static inline void BitmapAccumCounters(BitmapHeapScanState *node, TableScanDesc scan); static inline void BitmapDoneInitializingSharedState(ParallelBitmapHeapState *pstate); -static inline void BitmapAdjustPrefetchIterator(BitmapHeapScanState *node, - BlockNumber blockno); -static inline void BitmapAdjustPrefetchTarget(BitmapHeapScanState *node); -static inline void BitmapPrefetch(BitmapHeapScanState *node, - TableScanDesc scan); static bool BitmapShouldInitializeSharedState(ParallelBitmapHeapState *pstate); @@ -124,15 +119,6 @@ BitmapHeapNext(BitmapHeapScanState *node) node->tbm = tbm; tbmiterator = tbm_begin_iterate(tbm); - -#ifdef USE_PREFETCH - if (node->prefetch_maximum > 0) - { - node->prefetch_iterator = tbm_begin_iterate(tbm); - node->prefetch_pages = 0; - node->prefetch_target = -1; - } -#endif /* USE_PREFETCH */ } else { @@ -155,20 +141,6 @@ BitmapHeapNext(BitmapHeapScanState *node) * multiple processes to iterate jointly. */ pstate->tbmiterator = tbm_prepare_shared_iterate(tbm); -#ifdef USE_PREFETCH - if (node->prefetch_maximum > 0) - { - pstate->prefetch_iterator = - tbm_prepare_shared_iterate(tbm); - - /* - * We don't need the mutex here as we haven't yet woke up - * others. - */ - pstate->prefetch_pages = 0; - pstate->prefetch_target = -1; - } -#endif /* We have initialized the shared state so wake up others. */ BitmapDoneInitializingSharedState(pstate); @@ -176,14 +148,6 @@ BitmapHeapNext(BitmapHeapScanState *node) /* Allocate a private iterator and attach the shared state to it */ shared_tbmiterator = tbm_attach_shared_iterate(dsa, pstate->tbmiterator); - -#ifdef USE_PREFETCH - if (node->prefetch_maximum > 0) - { - node->shared_prefetch_iterator = - tbm_attach_shared_iterate(dsa, pstate->prefetch_iterator); - } -#endif /* USE_PREFETCH */ } if (!scan) @@ -203,46 +167,16 @@ BitmapHeapNext(BitmapHeapScanState *node) node->initialized = true; /* Get the first block. if none, end of scan */ - if (!table_scan_bitmap_next_block(scan, &node->recheck, &node->blockno)) + if (!table_scan_bitmap_next_block(scan, &node->recheck)) goto exit; - BitmapAdjustPrefetchIterator(node, node->blockno); - BitmapAdjustPrefetchTarget(node); } - for (;;) + do { while (table_scan_bitmap_next_tuple(scan, slot)) { CHECK_FOR_INTERRUPTS(); -#ifdef USE_PREFETCH - - /* - * Try to prefetch at least a few pages even before we get to the - * second page if we don't stop reading after the first tuple. - */ - if (!pstate) - { - if (node->prefetch_target < node->prefetch_maximum) - node->prefetch_target++; - } - else if (pstate->prefetch_target < node->prefetch_maximum) - { - /* take spinlock while updating shared state */ - SpinLockAcquire(&pstate->mutex); - if (pstate->prefetch_target < node->prefetch_maximum) - pstate->prefetch_target++; - SpinLockRelease(&pstate->mutex); - } -#endif /* USE_PREFETCH */ - - /* - * We prefetch before fetching the current pages. We expect that a - * future streaming read API will do this, so do it now for - * consistency. - */ - BitmapPrefetch(node, scan); - /* * If we are using lossy info, we have to recheck the qual * conditions at every tuple. @@ -263,13 +197,7 @@ BitmapHeapNext(BitmapHeapScanState *node) return slot; } - if (!table_scan_bitmap_next_block(scan, &node->recheck, &node->blockno)) - break; - - BitmapAdjustPrefetchIterator(node, node->blockno); - /* Adjust the prefetch target */ - BitmapAdjustPrefetchTarget(node); - } + } while (table_scan_bitmap_next_block(scan, &node->recheck)); /* * if we get here it means we are at the end of the scan.. @@ -304,215 +232,6 @@ BitmapDoneInitializingSharedState(ParallelBitmapHeapState *pstate) ConditionVariableBroadcast(&pstate->cv); } -/* - * BitmapAdjustPrefetchIterator - Adjust the prefetch iterator - */ -static inline void -BitmapAdjustPrefetchIterator(BitmapHeapScanState *node, - BlockNumber blockno) -{ -#ifdef USE_PREFETCH - ParallelBitmapHeapState *pstate = node->pstate; - - if (pstate == NULL) - { - TBMIterator *prefetch_iterator = node->prefetch_iterator; - - if (node->prefetch_pages > 0) - { - /* The main iterator has closed the distance by one page */ - node->prefetch_pages--; - } - else if (prefetch_iterator) - { - /* Do not let the prefetch iterator get behind the main one */ - TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator); - - if (tbmpre == NULL || tbmpre->blockno != blockno) - elog(ERROR, "prefetch and main iterators are out of sync"); - } - return; - } - - if (node->prefetch_maximum > 0) - { - TBMSharedIterator *prefetch_iterator = node->shared_prefetch_iterator; - - SpinLockAcquire(&pstate->mutex); - if (pstate->prefetch_pages > 0) - { - pstate->prefetch_pages--; - SpinLockRelease(&pstate->mutex); - } - else - { - /* Release the mutex before iterating */ - SpinLockRelease(&pstate->mutex); - - /* - * In case of shared mode, we can not ensure that the current - * blockno of the main iterator and that of the prefetch iterator - * are same. It's possible that whatever blockno we are - * prefetching will be processed by another process. Therefore, - * we don't validate the blockno here as we do in non-parallel - * case. - */ - if (prefetch_iterator) - tbm_shared_iterate(prefetch_iterator); - } - } -#endif /* USE_PREFETCH */ -} - -/* - * BitmapAdjustPrefetchTarget - Adjust the prefetch target - * - * Increase prefetch target if it's not yet at the max. Note that - * we will increase it to zero after fetching the very first - * page/tuple, then to one after the second tuple is fetched, then - * it doubles as later pages are fetched. - */ -static inline void -BitmapAdjustPrefetchTarget(BitmapHeapScanState *node) -{ -#ifdef USE_PREFETCH - ParallelBitmapHeapState *pstate = node->pstate; - - if (pstate == NULL) - { - if (node->prefetch_target >= node->prefetch_maximum) - /* don't increase any further */ ; - else if (node->prefetch_target >= node->prefetch_maximum / 2) - node->prefetch_target = node->prefetch_maximum; - else if (node->prefetch_target > 0) - node->prefetch_target *= 2; - else - node->prefetch_target++; - return; - } - - /* Do an unlocked check first to save spinlock acquisitions. */ - if (pstate->prefetch_target < node->prefetch_maximum) - { - SpinLockAcquire(&pstate->mutex); - if (pstate->prefetch_target >= node->prefetch_maximum) - /* don't increase any further */ ; - else if (pstate->prefetch_target >= node->prefetch_maximum / 2) - pstate->prefetch_target = node->prefetch_maximum; - else if (pstate->prefetch_target > 0) - pstate->prefetch_target *= 2; - else - pstate->prefetch_target++; - SpinLockRelease(&pstate->mutex); - } -#endif /* USE_PREFETCH */ -} - -/* - * BitmapPrefetch - Prefetch, if prefetch_pages are behind prefetch_target - */ -static inline void -BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan) -{ -#ifdef USE_PREFETCH - ParallelBitmapHeapState *pstate = node->pstate; - - if (pstate == NULL) - { - TBMIterator *prefetch_iterator = node->prefetch_iterator; - - if (prefetch_iterator) - { - while (node->prefetch_pages < node->prefetch_target) - { - TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator); - bool skip_fetch; - - if (tbmpre == NULL) - { - /* No more pages to prefetch */ - tbm_end_iterate(prefetch_iterator); - node->prefetch_iterator = NULL; - break; - } - node->prefetch_pages++; - - /* - * If we expect not to have to actually read this heap page, - * skip this prefetch call, but continue to run the prefetch - * logic normally. (Would it be better not to increment - * prefetch_pages?) - * - * This depends on the assumption that the index AM will - * report the same recheck flag for this future heap page as - * it did for the current heap page; which is not a certainty - * but is true in many cases. - */ - - skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH && - !tbmpre->recheck && - VM_ALL_VISIBLE(node->ss.ss_currentRelation, - tbmpre->blockno, - &node->pvmbuffer)); - - if (!skip_fetch) - PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno); - } - } - - return; - } - - if (pstate->prefetch_pages < pstate->prefetch_target) - { - TBMSharedIterator *prefetch_iterator = node->shared_prefetch_iterator; - - if (prefetch_iterator) - { - while (1) - { - TBMIterateResult *tbmpre; - bool do_prefetch = false; - bool skip_fetch; - - /* - * Recheck under the mutex. If some other process has already - * done enough prefetching then we need not to do anything. - */ - SpinLockAcquire(&pstate->mutex); - if (pstate->prefetch_pages < pstate->prefetch_target) - { - pstate->prefetch_pages++; - do_prefetch = true; - } - SpinLockRelease(&pstate->mutex); - - if (!do_prefetch) - return; - - tbmpre = tbm_shared_iterate(prefetch_iterator); - if (tbmpre == NULL) - { - /* No more pages to prefetch */ - tbm_end_shared_iterate(prefetch_iterator); - node->shared_prefetch_iterator = NULL; - break; - } - - /* As above, skip prefetch if we expect not to need page */ - skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH && - !tbmpre->recheck && - VM_ALL_VISIBLE(node->ss.ss_currentRelation, - tbmpre->blockno, - &node->pvmbuffer)); - - if (!skip_fetch) - PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno); - } - } - } -#endif /* USE_PREFETCH */ -} /* * BitmapHeapRecheck -- access method routine to recheck a tuple in EvalPlanQual @@ -559,22 +278,12 @@ ExecReScanBitmapHeapScan(BitmapHeapScanState *node) if (node->ss.ss_currentScanDesc) table_rescan(node->ss.ss_currentScanDesc, NULL); - /* release bitmaps and buffers if any */ - if (node->prefetch_iterator) - tbm_end_iterate(node->prefetch_iterator); - if (node->shared_prefetch_iterator) - tbm_end_shared_iterate(node->shared_prefetch_iterator); + /* release bitmaps if any */ if (node->tbm) tbm_free(node->tbm); - if (node->pvmbuffer != InvalidBuffer) - ReleaseBuffer(node->pvmbuffer); node->tbm = NULL; - node->prefetch_iterator = NULL; node->initialized = false; - node->shared_prefetch_iterator = NULL; - node->pvmbuffer = InvalidBuffer; node->recheck = true; - node->blockno = InvalidBlockNumber; ExecScanReScan(&node->ss); @@ -606,16 +315,10 @@ ExecEndBitmapHeapScan(BitmapHeapScanState *node) ExecEndNode(outerPlanState(node)); /* - * release bitmaps and buffers if any + * release bitmaps if any */ - if (node->prefetch_iterator) - tbm_end_iterate(node->prefetch_iterator); if (node->tbm) tbm_free(node->tbm); - if (node->shared_prefetch_iterator) - tbm_end_shared_iterate(node->shared_prefetch_iterator); - if (node->pvmbuffer != InvalidBuffer) - ReleaseBuffer(node->pvmbuffer); /* * close heap scan @@ -654,19 +357,13 @@ ExecInitBitmapHeapScan(BitmapHeapScan *node, EState *estate, int eflags) scanstate->ss.ps.ExecProcNode = ExecBitmapHeapScan; scanstate->tbm = NULL; - scanstate->pvmbuffer = InvalidBuffer; scanstate->exact_pages = 0; scanstate->lossy_pages = 0; - scanstate->prefetch_iterator = NULL; - scanstate->prefetch_pages = 0; - scanstate->prefetch_target = 0; scanstate->pscan_len = 0; scanstate->initialized = false; - scanstate->shared_prefetch_iterator = NULL; scanstate->pstate = NULL; scanstate->worker_snapshot = NULL; scanstate->recheck = true; - scanstate->blockno = InvalidBlockNumber; /* * Miscellaneous initialization @@ -706,13 +403,6 @@ ExecInitBitmapHeapScan(BitmapHeapScan *node, EState *estate, int eflags) scanstate->bitmapqualorig = ExecInitQual(node->bitmapqualorig, (PlanState *) scanstate); - /* - * Maximum number of prefetches for the tablespace if configured, - * otherwise the current value of the effective_io_concurrency GUC. - */ - scanstate->prefetch_maximum = - get_tablespace_io_concurrency(currentRelation->rd_rel->reltablespace); - scanstate->ss.ss_currentRelation = currentRelation; /* @@ -796,14 +486,10 @@ ExecBitmapHeapInitializeDSM(BitmapHeapScanState *node, return; pstate = shm_toc_allocate(pcxt->toc, node->pscan_len); - pstate->tbmiterator = 0; - pstate->prefetch_iterator = 0; /* Initialize the mutex */ SpinLockInit(&pstate->mutex); - pstate->prefetch_pages = 0; - pstate->prefetch_target = 0; pstate->state = BM_INITIAL; ConditionVariableInit(&pstate->cv); @@ -835,11 +521,7 @@ ExecBitmapHeapReInitializeDSM(BitmapHeapScanState *node, if (DsaPointerIsValid(pstate->tbmiterator)) tbm_free_shared_area(dsa, pstate->tbmiterator); - if (DsaPointerIsValid(pstate->prefetch_iterator)) - tbm_free_shared_area(dsa, pstate->prefetch_iterator); - pstate->tbmiterator = InvalidDsaPointer; - pstate->prefetch_iterator = InvalidDsaPointer; } /* ---------------------------------------------------------------- diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c index 0f4850065fb..ccb511fb608 100644 --- a/src/backend/nodes/tidbitmap.c +++ b/src/backend/nodes/tidbitmap.c @@ -180,7 +180,6 @@ struct TBMIterator int spageptr; /* next spages index */ int schunkptr; /* next schunks index */ int schunkbit; /* next bit to check in current schunk */ - TBMIterateResult output; /* MUST BE LAST (because variable-size) */ }; /* @@ -221,7 +220,6 @@ struct TBMSharedIterator PTEntryArray *ptbase; /* pagetable element array */ PTIterationArray *ptpages; /* sorted exact page index list */ PTIterationArray *ptchunks; /* sorted lossy page index list */ - TBMIterateResult output; /* MUST BE LAST (because variable-size) */ }; /* Local function prototypes */ @@ -695,8 +693,7 @@ tbm_begin_iterate(TIDBitmap *tbm) * Create the TBMIterator struct, with enough trailing space to serve the * needs of the TBMIterateResult sub-struct. */ - iterator = (TBMIterator *) palloc(sizeof(TBMIterator) + - MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber)); + iterator = (TBMIterator *) palloc(sizeof(TBMIterator)); iterator->tbm = tbm; /* @@ -957,20 +954,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp) /* * tbm_iterate - scan through next page of a TIDBitmap * - * Returns a TBMIterateResult representing one page, or NULL if there are - * no more pages to scan. Pages are guaranteed to be delivered in numerical - * order. If result->ntuples < 0, then the bitmap is "lossy" and failed to - * remember the exact tuples to look at on this page --- the caller must - * examine all tuples on the page and check if they meet the intended - * condition. If result->recheck is true, only the indicated tuples need - * be examined, but the condition must be rechecked anyway. (For ease of - * testing, recheck is always set true when ntuples < 0.) + * Caller must pass in a TBMIterateResult to be filled. + * + * Pages are guaranteed to be delivered in numerical order. tbmres->blockno is + * set to InvalidBlockNumber when there are no more pages to scan. If + * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the + * exact tuples to look at on this page --- the caller must examine all tuples + * on the page and check if they meet the intended condition. If + * tbmres->recheck is true, only the indicated tuples need be examined, but the + * condition must be rechecked anyway. (For ease of testing, recheck is always + * set true when ntuples < 0.) */ -TBMIterateResult * -tbm_iterate(TBMIterator *iterator) +void +tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres) { TIDBitmap *tbm = iterator->tbm; - TBMIterateResult *output = &(iterator->output); Assert(tbm->iterating == TBM_ITERATING_PRIVATE); @@ -998,6 +996,7 @@ tbm_iterate(TBMIterator *iterator) * If both chunk and per-page data remain, must output the numerically * earlier page. */ + Assert(tbmres); if (iterator->schunkptr < tbm->nchunks) { PagetableEntry *chunk = tbm->schunks[iterator->schunkptr]; @@ -1008,11 +1007,11 @@ tbm_iterate(TBMIterator *iterator) chunk_blockno < tbm->spages[iterator->spageptr]->blockno) { /* Return a lossy page indicator from the chunk */ - output->blockno = chunk_blockno; - output->ntuples = -1; - output->recheck = true; + tbmres->blockno = chunk_blockno; + tbmres->ntuples = -1; + tbmres->recheck = true; iterator->schunkbit++; - return output; + return; } } @@ -1028,18 +1027,20 @@ tbm_iterate(TBMIterator *iterator) page = tbm->spages[iterator->spageptr]; /* scan bitmap to extract individual offset numbers */ - ntuples = tbm_extract_page_tuple(page, output); - output->blockno = page->blockno; - output->ntuples = ntuples; - output->recheck = page->recheck; + ntuples = tbm_extract_page_tuple(page, tbmres); + tbmres->blockno = page->blockno; + tbmres->ntuples = ntuples; + tbmres->recheck = page->recheck; iterator->spageptr++; - return output; + return; } /* Nothing more in the bitmap */ - return NULL; + tbmres->blockno = InvalidBlockNumber; + return; } + /* * tbm_shared_iterate - scan through next page of a TIDBitmap * @@ -1047,10 +1048,9 @@ tbm_iterate(TBMIterator *iterator) * across multiple processes. We need to acquire the iterator LWLock, * before accessing the shared members. */ -TBMIterateResult * -tbm_shared_iterate(TBMSharedIterator *iterator) +void +tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres) { - TBMIterateResult *output = &iterator->output; TBMSharedIteratorState *istate = iterator->state; PagetableEntry *ptbase = NULL; int *idxpages = NULL; @@ -1101,13 +1101,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator) chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno) { /* Return a lossy page indicator from the chunk */ - output->blockno = chunk_blockno; - output->ntuples = -1; - output->recheck = true; + tbmres->blockno = chunk_blockno; + tbmres->ntuples = -1; + tbmres->recheck = true; istate->schunkbit++; LWLockRelease(&istate->lock); - return output; + return; } } @@ -1117,21 +1117,22 @@ tbm_shared_iterate(TBMSharedIterator *iterator) int ntuples; /* scan bitmap to extract individual offset numbers */ - ntuples = tbm_extract_page_tuple(page, output); - output->blockno = page->blockno; - output->ntuples = ntuples; - output->recheck = page->recheck; + ntuples = tbm_extract_page_tuple(page, tbmres); + tbmres->blockno = page->blockno; + tbmres->ntuples = ntuples; + tbmres->recheck = page->recheck; istate->spageptr++; LWLockRelease(&istate->lock); - return output; + return; } LWLockRelease(&istate->lock); /* Nothing more in the bitmap */ - return NULL; + tbmres->blockno = InvalidBlockNumber; + return; } /* @@ -1470,8 +1471,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp) * Create the TBMSharedIterator struct, with enough trailing space to * serve the needs of the TBMIterateResult sub-struct. */ - iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) + - MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber)); + iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator)); istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp); diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h index 2fc369a18ff..33e8a7e0bba 100644 --- a/src/include/access/heapam.h +++ b/src/include/access/heapam.h @@ -26,6 +26,7 @@ #include "storage/dsm.h" #include "storage/lockdefs.h" #include "storage/shm_toc.h" +#include "storage/streaming_read.h" #include "utils/relcache.h" #include "utils/snapshot.h" @@ -73,6 +74,7 @@ typedef struct HeapScanDescData ParallelBlockTableScanWorkerData *rs_parallelworkerdata; /* these fields only used in page-at-a-time mode and for bitmap scans */ + PgStreamingRead *pgsr; Buffer vmbuffer; /* for checking if can skip fetch */ int empty_tuples; /* count of all NULL tuples to be returned */ int rs_cindex; /* current tuple's index in vistuples */ diff --git a/src/include/access/tableam.h b/src/include/access/tableam.h index b90d9b7f3fa..adde320d1eb 100644 --- a/src/include/access/tableam.h +++ b/src/include/access/tableam.h @@ -788,17 +788,10 @@ typedef struct TableAmRoutine * on the page have to be returned, otherwise the tuples at offsets in * `tbmres->offsets` need to be returned. * - * XXX: Currently this may only be implemented if the AM uses md.c as its - * storage manager, and uses ItemPointer->ip_blkid in a manner that maps - * blockids directly to the underlying storage. nodeBitmapHeapscan.c - * performs prefetching directly using that interface. This probably - * needs to be rectified at a later point. - * * Optional callback, but either both scan_bitmap_next_block and * scan_bitmap_next_tuple need to exist, or neither. */ - bool (*scan_bitmap_next_block) (TableScanDesc scan, - bool *recheck, BlockNumber *blockno); + bool (*scan_bitmap_next_block) (TableScanDesc scan, bool *recheck); /* * Fetch the next tuple of a bitmap table scan into `slot` and return true @@ -1950,8 +1943,7 @@ table_relation_estimate_size(Relation rel, int32 *attr_widths, * used after verifying the presence (at plan time or such). */ static inline bool -table_scan_bitmap_next_block(TableScanDesc scan, - bool *recheck, BlockNumber *blockno) +table_scan_bitmap_next_block(TableScanDesc scan, bool *recheck) { /* * We don't expect direct calls to table_scan_bitmap_next_block with valid @@ -1961,7 +1953,7 @@ table_scan_bitmap_next_block(TableScanDesc scan, if (unlikely(TransactionIdIsValid(CheckXidAlive) && !bsysscan)) elog(ERROR, "unexpected table_scan_bitmap_next_block call during logical decoding"); - return scan->rs_rd->rd_tableam->scan_bitmap_next_block(scan, recheck, blockno); + return scan->rs_rd->rd_tableam->scan_bitmap_next_block(scan, recheck); } /* diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h index 03973a3f262..96afabc67e6 100644 --- a/src/include/nodes/execnodes.h +++ b/src/include/nodes/execnodes.h @@ -1682,11 +1682,8 @@ typedef enum /* ---------------- * ParallelBitmapHeapState information * tbmiterator iterator for scanning current pages - * prefetch_iterator iterator for prefetching ahead of current page * mutex mutual exclusion for the prefetching variable * and state - * prefetch_pages # pages prefetch iterator is ahead of current - * prefetch_target current target prefetch distance * state current state of the TIDBitmap * cv conditional wait variable * phs_snapshot_data snapshot data shared to workers @@ -1695,10 +1692,7 @@ typedef enum typedef struct ParallelBitmapHeapState { dsa_pointer tbmiterator; - dsa_pointer prefetch_iterator; slock_t mutex; - int prefetch_pages; - int prefetch_target; SharedBitmapState state; ConditionVariable cv; char phs_snapshot_data[FLEXIBLE_ARRAY_MEMBER]; @@ -1709,16 +1703,10 @@ typedef struct ParallelBitmapHeapState * * bitmapqualorig execution state for bitmapqualorig expressions * tbm bitmap obtained from child index scan(s) - * pvmbuffer buffer for visibility-map lookups of prefetched pages * exact_pages total number of exact pages retrieved * 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 - * prefetch_maximum maximum value for prefetch_target * pscan_len size of the shared memory for parallel bitmap * initialized is node is ready to iterate - * shared_prefetch_iterator shared iterator for prefetching * pstate shared state for parallel bitmap scan * worker_snapshot snapshot for parallel worker * ---------------- @@ -1728,20 +1716,13 @@ typedef struct BitmapHeapScanState ScanState ss; /* its first field is NodeTag */ ExprState *bitmapqualorig; TIDBitmap *tbm; - Buffer pvmbuffer; long exact_pages; long lossy_pages; - TBMIterator *prefetch_iterator; - int prefetch_pages; - int prefetch_target; - int prefetch_maximum; Size pscan_len; bool initialized; - TBMSharedIterator *shared_prefetch_iterator; ParallelBitmapHeapState *pstate; Snapshot worker_snapshot; bool recheck; - BlockNumber blockno; } BitmapHeapScanState; /* ---------------- diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h index 1945f0639bf..672608200ba 100644 --- a/src/include/nodes/tidbitmap.h +++ b/src/include/nodes/tidbitmap.h @@ -64,12 +64,16 @@ extern bool tbm_is_empty(const TIDBitmap *tbm); extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm); extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm); -extern TBMIterateResult *tbm_iterate(TBMIterator *iterator); -extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator); +extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres); +extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres); extern void tbm_end_iterate(TBMIterator *iterator); extern void tbm_end_shared_iterate(TBMSharedIterator *iterator); extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp); extern long tbm_calculate_entries(double maxbytes); +#define TBM_ITERATE_RESULT_SIZE \ + (offsetof(TBMIterateResult, offsets) + \ + MaxHeapTuplesPerPage * sizeof(OffsetNumber)) + #endif /* TIDBITMAP_H */ -- 2.37.2