From fbf0772603f00d4230f1382ae5d2d7640d62ed49 Mon Sep 17 00:00:00 2001 From: Melanie Plageman Date: Fri, 17 Jan 2025 17:20:28 -0500 Subject: [PATCH v28 2/4] Separate TBM[Shared|Private]Iterator and TBMIterateResult Remove the TBMIterateResult member from the TBMPrivateIterator and TBMSharedIterator and make tbm_[shared|private_]iterate() take a TBMIterateResult as a parameter. This will allow multiple TBMIterateResults to exist concurrently, allowing asynchronous use of the TIDBitmap for prefetching. tbm_[shared|private]_iterate() now sets blockno to InvalidBlockNumber when the bitmap is exhausted instead of returning NULL. BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally and pass it in. Because GIN only needs a single TBMIterateResult, we inline the matchResult in the GinScanEntry to avoid having to separately manage memory for the TBMIterateResult. --- src/backend/access/gin/ginget.c | 40 ++++++------ src/backend/access/gin/ginscan.c | 3 +- src/backend/access/heap/heapam_handler.c | 30 ++++----- src/backend/executor/nodeBitmapHeapscan.c | 40 ++++++------ src/backend/nodes/tidbitmap.c | 79 +++++++++++------------ src/include/access/gin_private.h | 7 +- src/include/nodes/tidbitmap.h | 6 +- 7 files changed, 106 insertions(+), 99 deletions(-) diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c index 330805626ee..ddf9976ae12 100644 --- a/src/backend/access/gin/ginget.c +++ b/src/backend/access/gin/ginget.c @@ -332,10 +332,12 @@ restartScanEntry: entry->list = NULL; entry->nlist = 0; entry->matchBitmap = NULL; - entry->matchResult = NULL; + entry->matchResult = (TBMIterateResult) {0}; + entry->matchResult.blockno = InvalidBlockNumber; entry->reduceResult = false; entry->predictNumberResult = 0; + /* * we should find entry, and begin scan of posting tree or just store * posting list in memory @@ -824,19 +826,19 @@ 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_private_iterate() sets matchResult->blockno + * to InvalidBlockNumber when the bitmap is exhausted. */ - while (entry->matchResult == NULL || - (entry->matchResult->ntuples >= 0 && - entry->offset >= entry->matchResult->ntuples) || - entry->matchResult->blockno < advancePastBlk || + 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.blockno == advancePastBlk)) { - entry->matchResult = - tbm_private_iterate(entry->matchIterator); + tbm_private_iterate(entry->matchIterator, &entry->matchResult); - if (entry->matchResult == NULL) + if (!BlockNumberIsValid(entry->matchResult.blockno)) { ItemPointerSetInvalid(&entry->curItem); tbm_end_private_iterate(entry->matchIterator); @@ -847,7 +849,7 @@ entryGetItem(GinState *ginstate, GinScanEntry entry, /* * Reset counter to the beginning of entry->matchResult. Note: - * entry->offset is still greater than matchResult->ntuples if + * entry->offset is still greater than matchResult.ntuples if * matchResult is lossy. So, on next call we will get next * result from TIDBitmap. */ @@ -860,10 +862,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry, * We're now on the first page after advancePast which has any * items on it. If it's a lossy result, return that. */ - if (entry->matchResult->ntuples < 0) + if (entry->matchResult.ntuples < 0) { ItemPointerSetLossyPage(&entry->curItem, - entry->matchResult->blockno); + entry->matchResult.blockno); /* * We might as well fall out of the loop; we could not @@ -877,27 +879,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry, * Not a lossy page. Skip over any offsets <= advancePast, and * return that. */ - if (entry->matchResult->blockno == advancePastBlk) + if (entry->matchResult.blockno == advancePastBlk) { /* * First, do a quick check against the last offset on the * page. If that's > advancePast, so are all the other * offsets, so just go back to the top to get the next page. */ - if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff) + if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff) { - entry->offset = entry->matchResult->ntuples; + entry->offset = entry->matchResult.ntuples; continue; } /* Otherwise scan to find the first item > advancePast */ - while (entry->matchResult->offsets[entry->offset] <= advancePastOff) + while (entry->matchResult.offsets[entry->offset] <= advancePastOff) entry->offset++; } ItemPointerSet(&entry->curItem, - entry->matchResult->blockno, - entry->matchResult->offsets[entry->offset]); + entry->matchResult.blockno, + entry->matchResult.offsets[entry->offset]); entry->offset++; /* Done unless we need to reduce the result */ diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c index 7d1e6615260..5e6dd514cc4 100644 --- a/src/backend/access/gin/ginscan.c +++ b/src/backend/access/gin/ginscan.c @@ -106,7 +106,8 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum, ItemPointerSetMin(&scanEntry->curItem); scanEntry->matchBitmap = NULL; scanEntry->matchIterator = NULL; - scanEntry->matchResult = NULL; + scanEntry->matchResult = (TBMIterateResult) {0}; + scanEntry->matchResult.blockno = InvalidBlockNumber; scanEntry->list = NULL; scanEntry->nlist = 0; scanEntry->offset = InvalidOffsetNumber; diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index a4003cf59e1..bd567760f2d 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -2124,7 +2124,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan, Buffer buffer; Snapshot snapshot; int ntup; - TBMIterateResult *tbmres; + TBMIterateResult tbmres; Assert(scan->rs_flags & SO_TYPE_BITMAPSCAN); @@ -2138,9 +2138,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan, { CHECK_FOR_INTERRUPTS(); - tbmres = tbm_iterate(&scan->st.rs_tbmiterator); + tbm_iterate(&scan->st.rs_tbmiterator, &tbmres); - if (tbmres == NULL) + if (!BlockNumberIsValid(tbmres.blockno)) return false; /* @@ -2152,11 +2152,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan, * reachable by the index. */ } while (!IsolationIsSerializable() && - tbmres->blockno >= hscan->rs_nblocks); + tbmres.blockno >= hscan->rs_nblocks); /* Got a valid block */ - *blockno = tbmres->blockno; - *recheck = tbmres->recheck; + *blockno = tbmres.blockno; + *recheck = tbmres.recheck; /* * We can skip fetching the heap page if we don't need any fields from the @@ -2164,19 +2164,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan, * page are visible to our transaction. */ if (!(scan->rs_flags & SO_NEED_TUPLES) && - !tbmres->recheck && - VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &bscan->rs_vmbuffer)) + !tbmres.recheck && + VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &bscan->rs_vmbuffer)) { /* can't be lossy in the skip_fetch case */ - Assert(tbmres->ntuples >= 0); + Assert(tbmres.ntuples >= 0); Assert(bscan->rs_empty_tuples_pending >= 0); - bscan->rs_empty_tuples_pending += tbmres->ntuples; + bscan->rs_empty_tuples_pending += tbmres.ntuples; return true; } - block = tbmres->blockno; + block = tbmres.blockno; /* * Acquire pin on the target heap page, trading in any pin we held before. @@ -2205,7 +2205,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan, /* * We need two separate strategies for lossy and non-lossy cases. */ - if (tbmres->ntuples >= 0) + if (tbmres.ntuples >= 0) { /* * Bitmap is non-lossy, so we just look through the offsets listed in @@ -2214,9 +2214,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan, */ int curslot; - for (curslot = 0; curslot < tbmres->ntuples; curslot++) + for (curslot = 0; curslot < tbmres.ntuples; curslot++) { - OffsetNumber offnum = tbmres->offsets[curslot]; + OffsetNumber offnum = tbmres.offsets[curslot]; ItemPointerData tid; HeapTupleData heapTuple; @@ -2266,7 +2266,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan, Assert(ntup <= MaxHeapTuplesPerPage); hscan->rs_ntuples = ntup; - if (tbmres->ntuples >= 0) + if (tbmres.ntuples >= 0) (*exact_pages)++; else (*lossy_pages)++; diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c index be0d24d901b..32dea13cb86 100644 --- a/src/backend/executor/nodeBitmapHeapscan.c +++ b/src/backend/executor/nodeBitmapHeapscan.c @@ -317,7 +317,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node) { #ifdef USE_PREFETCH ParallelBitmapHeapState *pstate = node->pstate; - TBMIterateResult *tbmpre; + TBMIterateResult tbmpre; if (pstate == NULL) { @@ -330,9 +330,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node) } else if (!tbm_exhausted(prefetch_iterator)) { - tbmpre = tbm_iterate(prefetch_iterator); - node->prefetch_blockno = tbmpre ? tbmpre->blockno : - InvalidBlockNumber; + tbm_iterate(prefetch_iterator, &tbmpre); + node->prefetch_blockno = tbmpre.blockno; } return; } @@ -371,9 +370,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node) */ if (!tbm_exhausted(prefetch_iterator)) { - tbmpre = tbm_iterate(prefetch_iterator); - node->prefetch_blockno = tbmpre ? tbmpre->blockno : - InvalidBlockNumber; + tbm_iterate(prefetch_iterator, &tbmpre); + node->prefetch_blockno = tbmpre.blockno; } } } @@ -441,17 +439,19 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan) { while (node->prefetch_pages < node->prefetch_target) { - TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator); + TBMIterateResult tbmpre; bool skip_fetch; - if (tbmpre == NULL) + tbm_iterate(prefetch_iterator, &tbmpre); + + if (!BlockNumberIsValid(tbmpre.blockno)) { /* No more pages to prefetch */ tbm_end_iterate(prefetch_iterator); break; } node->prefetch_pages++; - node->prefetch_blockno = tbmpre->blockno; + node->prefetch_blockno = tbmpre.blockno; /* * If we expect not to have to actually read this heap page, @@ -460,13 +460,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan) * prefetch_pages?) */ skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLES) && - !tbmpre->recheck && + !tbmpre.recheck && VM_ALL_VISIBLE(node->ss.ss_currentRelation, - tbmpre->blockno, + tbmpre.blockno, &node->pvmbuffer)); if (!skip_fetch) - PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno); + PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno); } } @@ -481,7 +481,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan) { while (1) { - TBMIterateResult *tbmpre; + TBMIterateResult tbmpre; bool do_prefetch = false; bool skip_fetch; @@ -500,25 +500,25 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan) if (!do_prefetch) return; - tbmpre = tbm_iterate(prefetch_iterator); - if (tbmpre == NULL) + tbm_iterate(prefetch_iterator, &tbmpre); + if (!BlockNumberIsValid(tbmpre.blockno)) { /* No more pages to prefetch */ tbm_end_iterate(prefetch_iterator); break; } - node->prefetch_blockno = tbmpre->blockno; + node->prefetch_blockno = tbmpre.blockno; /* As above, skip prefetch if we expect not to need page */ skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLES) && - !tbmpre->recheck && + !tbmpre.recheck && VM_ALL_VISIBLE(node->ss.ss_currentRelation, - tbmpre->blockno, + tbmpre.blockno, &node->pvmbuffer)); if (!skip_fetch) - PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno); + PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno); } } } diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c index 3d38cc04cc5..40d7b9f7505 100644 --- a/src/backend/nodes/tidbitmap.c +++ b/src/backend/nodes/tidbitmap.c @@ -172,7 +172,6 @@ struct TBMPrivateIterator int spageptr; /* next spages index */ int schunkptr; /* next schunks index */ int schunkbit; /* next bit to check in current schunk */ - TBMIterateResult output; }; /* @@ -213,7 +212,6 @@ struct TBMSharedIterator PTEntryArray *ptbase; /* pagetable element array */ PTIterationArray *ptpages; /* sorted exact page index list */ PTIterationArray *ptchunks; /* sorted lossy page index list */ - TBMIterateResult output; }; /* Local function prototypes */ @@ -948,20 +946,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp) /* * tbm_private_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_private_iterate(TBMPrivateIterator *iterator) +void +tbm_private_iterate(TBMPrivateIterator *iterator, TBMIterateResult *tbmres) { TIDBitmap *tbm = iterator->tbm; - TBMIterateResult *output = &(iterator->output); Assert(tbm->iterating == TBM_ITERATING_PRIVATE); @@ -999,11 +998,11 @@ tbm_private_iterate(TBMPrivateIterator *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; } } @@ -1019,16 +1018,16 @@ tbm_private_iterate(TBMPrivateIterator *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; } /* @@ -1038,10 +1037,9 @@ tbm_private_iterate(TBMPrivateIterator *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; @@ -1092,13 +1090,13 @@ 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; } } @@ -1108,21 +1106,21 @@ 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; } /* @@ -1598,13 +1596,14 @@ tbm_end_iterate(TBMIterator *iterator) /* * Get the next TBMIterateResult from the shared or private bitmap iterator. */ -TBMIterateResult * -tbm_iterate(TBMIterator *iterator) +void +tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres) { Assert(iterator); + Assert(tbmres); if (iterator->shared) - return tbm_shared_iterate(iterator->i.shared_iterator); + return tbm_shared_iterate(iterator->i.shared_iterator, tbmres); else - return tbm_private_iterate(iterator->i.private_iterator); + return tbm_private_iterate(iterator->i.private_iterator, tbmres); } diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h index dcd1ae3fc34..478e2a8a377 100644 --- a/src/include/access/gin_private.h +++ b/src/include/access/gin_private.h @@ -353,7 +353,12 @@ typedef struct GinScanEntryData /* for a partial-match or full-scan query, we accumulate all TIDs here */ TIDBitmap *matchBitmap; TBMPrivateIterator *matchIterator; - TBMIterateResult *matchResult; + + /* + * If blockno is InvalidBlockNumber, all of the other fields in the + * matchResult are meaningless. + */ + TBMIterateResult matchResult; /* used for Posting list and one page in Posting tree */ ItemPointerData *list; diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h index b2e322508a2..f3956d5171e 100644 --- a/src/include/nodes/tidbitmap.h +++ b/src/include/nodes/tidbitmap.h @@ -86,8 +86,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm); extern TBMPrivateIterator *tbm_begin_private_iterate(TIDBitmap *tbm); extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm); -extern TBMIterateResult *tbm_private_iterate(TBMPrivateIterator *iterator); -extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator); +extern void tbm_private_iterate(TBMPrivateIterator *iterator, TBMIterateResult *tbmres); +extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres); extern void tbm_end_private_iterate(TBMPrivateIterator *iterator); extern void tbm_end_shared_iterate(TBMSharedIterator *iterator); extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa, @@ -98,7 +98,7 @@ extern TBMIterator tbm_begin_iterate(TIDBitmap *tbm, dsa_area *dsa, dsa_pointer dsp); extern void tbm_end_iterate(TBMIterator *iterator); -extern TBMIterateResult *tbm_iterate(TBMIterator *iterator); +extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres); static inline bool tbm_exhausted(TBMIterator *iterator) -- 2.45.2