Re: bitmapscan changes patch review - Mailing list pgsql-patches
| From | Joshua D. Drake |
|---|---|
| Subject | Re: bitmapscan changes patch review |
| Date | |
| Msg-id | 467BDC1F.6060600@commandprompt.com Whole thread Raw |
| In response to | bitmapscan changes patch review (Alexey Klyukin <alexk@commandprompt.com>) |
| List | pgsql-patches |
Alexey Klyukin wrote: > Hi, > > Here is a patch by Heikki Linnakangas with changes for amgetmulti index > access method to amgetbitmap, which returns all matching tuples at once. > The patch also introduces support for candidate matches. The original > post is here: > http://archives.postgresql.org/pgsql-patches/2007-03/msg00163.php > > I've made minor changes to the patch: > > - fixed all rejects when applying it to the current CVS head. > - fixed counting ntids in gistnext if TIDBitmap is not null. > - added missing expected/bitmapops.out > > It passes all regression tests on my system. Any comments on the below? Sincerely, Joshua D. Drake > > Regards, > > > ------------------------------------------------------------------------ > > diff -c -N -r ./src/backend/access/gin/ginget.c ../pgsql.new/src/backend/access/gin/ginget.c > *** ./src/backend/access/gin/ginget.c 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/backend/access/gin/ginget.c 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 476,509 **** > #define GinIsVoidRes(s) ( ((GinScanOpaque) scan->opaque)->isVoidRes == true ) > > Datum > ! gingetmulti(PG_FUNCTION_ARGS) > { > IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0); > ! ItemPointer tids = (ItemPointer) PG_GETARG_POINTER(1); > ! int32 max_tids = PG_GETARG_INT32(2); > ! int32 *returned_tids = (int32 *) PG_GETARG_POINTER(3); > > if (GinIsNewKey(scan)) > newScanKey(scan); > > - *returned_tids = 0; > - > if (GinIsVoidRes(scan)) > ! PG_RETURN_BOOL(false); > > startScan(scan); > > ! do > { > ! if (scanGetItem(scan, tids + *returned_tids)) > ! (*returned_tids)++; > ! else > break; > ! } while (*returned_tids < max_tids); > > stopScan(scan); > > ! PG_RETURN_BOOL(*returned_tids == max_tids); > } > > Datum > --- 476,510 ---- > #define GinIsVoidRes(s) ( ((GinScanOpaque) scan->opaque)->isVoidRes == true ) > > Datum > ! gingetbitmap(PG_FUNCTION_ARGS) > { > IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0); > ! TIDBitmap *tbm = (TIDBitmap *) PG_GETARG_POINTER(1); > ! int32 ntids; > > if (GinIsNewKey(scan)) > newScanKey(scan); > > if (GinIsVoidRes(scan)) > ! PG_RETURN_INT32(0); > > startScan(scan); > > ! ntids = 0; > ! for(;;) > { > ! ItemPointerData iptr; > ! > ! if (!scanGetItem(scan, &iptr)) > break; > ! > ! ntids++; > ! tbm_add_tuples(tbm, &iptr, 1, false); > ! } > > stopScan(scan); > > ! PG_RETURN_INT32(ntids); > } > > Datum > diff -c -N -r ./src/backend/access/gist/gistget.c ../pgsql.new/src/backend/access/gist/gistget.c > *** ./src/backend/access/gist/gistget.c 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/backend/access/gist/gistget.c 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 22,28 **** > > static OffsetNumber gistfindnext(IndexScanDesc scan, OffsetNumber n, > ScanDirection dir); > ! static int gistnext(IndexScanDesc scan, ScanDirection dir, ItemPointer tids, int maxtids, bool ignore_killed_tuples); > static bool gistindex_keytest(IndexTuple tuple, IndexScanDesc scan, > OffsetNumber offset); > > --- 22,30 ---- > > static OffsetNumber gistfindnext(IndexScanDesc scan, OffsetNumber n, > ScanDirection dir); > ! static int gistnext(IndexScanDesc scan, ScanDirection dir, > ! ItemPointer tid, TIDBitmap *tbm, > ! bool ignore_killed_tuples); > static bool gistindex_keytest(IndexTuple tuple, IndexScanDesc scan, > OffsetNumber offset); > > *************** > *** 114,145 **** > * tuples, continue looping until we find a non-killed tuple that matches > * the search key. > */ > ! res = (gistnext(scan, dir, &tid, 1, scan->ignore_killed_tuples)) ? true : false; > > PG_RETURN_BOOL(res); > } > > Datum > ! gistgetmulti(PG_FUNCTION_ARGS) > { > IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0); > ! ItemPointer tids = (ItemPointer) PG_GETARG_POINTER(1); > ! int32 max_tids = PG_GETARG_INT32(2); > ! int32 *returned_tids = (int32 *) PG_GETARG_POINTER(3); > > ! *returned_tids = gistnext(scan, ForwardScanDirection, tids, max_tids, false); > > ! PG_RETURN_BOOL(*returned_tids == max_tids); > } > > /* > * Fetch a tuples that matchs the search key; this can be invoked > * either to fetch the first such tuple or subsequent matching > ! * tuples. Returns true iff a matching tuple was found. > */ > static int > ! gistnext(IndexScanDesc scan, ScanDirection dir, ItemPointer tids, > ! int maxtids, bool ignore_killed_tuples) > { > Page p; > OffsetNumber n; > --- 116,152 ---- > * tuples, continue looping until we find a non-killed tuple that matches > * the search key. > */ > ! res = (gistnext(scan, dir, &tid, NULL, scan->ignore_killed_tuples)) ? true : false; > > PG_RETURN_BOOL(res); > } > > Datum > ! gistgetbitmap(PG_FUNCTION_ARGS) > { > IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0); > ! TIDBitmap *tbm = (TIDBitmap *) PG_GETARG_POINTER(1); > ! int32 ntids; > > ! ntids = gistnext(scan, ForwardScanDirection, NULL, tbm, false); > > ! PG_RETURN_INT32(ntids); > } > > /* > * Fetch a tuples that matchs the search key; this can be invoked > * either to fetch the first such tuple or subsequent matching > ! * tuples. > ! * > ! * This function is used by both gistgettuple and gistgetbitmap. When > ! * invoked from gistgettuple, tbm is null and the next matching tuple > ! * is returned in *tid. When invoked from getbitmap, tid is null and > ! * all matching tuples are added to tbm and tid is null. In both cases, > ! * the number of returned tuples is returned. > */ > static int > ! gistnext(IndexScanDesc scan, ScanDirection dir, ItemPointer tid, > ! TIDBitmap *tbm, bool ignore_killed_tuples) > { > Page p; > OffsetNumber n; > *************** > *** 292,304 **** > if (!(ignore_killed_tuples && ItemIdDeleted(PageGetItemId(p, n)))) > { > it = (IndexTuple) PageGetItem(p, PageGetItemId(p, n)); > - tids[ntids] = scan->xs_ctup.t_self = it->t_tid; > ntids++; > ! > ! if (ntids == maxtids) > { > LockBuffer(so->curbuf, GIST_UNLOCK); > ! return ntids; > } > } > } > --- 299,313 ---- > if (!(ignore_killed_tuples && ItemIdDeleted(PageGetItemId(p, n)))) > { > it = (IndexTuple) PageGetItem(p, PageGetItemId(p, n)); > ntids++; > ! if(tbm != NULL) > ! tbm_add_tuples(tbm, &it->t_tid, 1, false); > ! else > { > + *tid = scan->xs_ctup.t_self = it->t_tid; > + > LockBuffer(so->curbuf, GIST_UNLOCK); > ! return ntids; /* always 1 */ > } > } > } > diff -c -N -r ./src/backend/access/hash/hash.c ../pgsql.new/src/backend/access/hash/hash.c > *** ./src/backend/access/hash/hash.c 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/backend/access/hash/hash.c 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 239,310 **** > > > /* > ! * hashgetmulti() -- get multiple tuples at once > ! * > ! * This is a somewhat generic implementation: it avoids lock reacquisition > ! * overhead, but there's no smarts about picking especially good stopping > ! * points such as index page boundaries. > */ > Datum > ! hashgetmulti(PG_FUNCTION_ARGS) > { > IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0); > ! ItemPointer tids = (ItemPointer) PG_GETARG_POINTER(1); > ! int32 max_tids = PG_GETARG_INT32(2); > ! int32 *returned_tids = (int32 *) PG_GETARG_POINTER(3); > HashScanOpaque so = (HashScanOpaque) scan->opaque; > - Relation rel = scan->indexRelation; > bool res = true; > int32 ntids = 0; > > ! /* > ! * We hold pin but not lock on current buffer while outside the hash AM. > ! * Reacquire the read lock here. > ! */ > ! if (BufferIsValid(so->hashso_curbuf)) > ! _hash_chgbufaccess(rel, so->hashso_curbuf, HASH_NOLOCK, HASH_READ); > > ! while (ntids < max_tids) > { > ! /* > ! * Start scan, or advance to next tuple. > ! */ > ! if (ItemPointerIsValid(&(so->hashso_curpos))) > ! res = _hash_next(scan, ForwardScanDirection); > ! else > ! res = _hash_first(scan, ForwardScanDirection); > ! > /* > * Skip killed tuples if asked to. > */ > if (scan->ignore_killed_tuples) > { > ! while (res) > ! { > ! Page page; > ! OffsetNumber offnum; > > ! offnum = ItemPointerGetOffsetNumber(&(so->hashso_curpos)); > ! page = BufferGetPage(so->hashso_curbuf); > ! if (!ItemIdDeleted(PageGetItemId(page, offnum))) > ! break; > ! res = _hash_next(scan, ForwardScanDirection); > ! } > } > > - if (!res) > - break; > /* Save tuple ID, and continue scanning */ > ! tids[ntids] = scan->xs_ctup.t_self; > ! ntids++; > ! } > > ! /* Release read lock on current buffer, but keep it pinned */ > ! if (BufferIsValid(so->hashso_curbuf)) > ! _hash_chgbufaccess(rel, so->hashso_curbuf, HASH_READ, HASH_NOLOCK); > > ! *returned_tids = ntids; > ! PG_RETURN_BOOL(res); > } > > > --- 239,286 ---- > > > /* > ! * hashgetbitmap() -- get multiple tuples at once > */ > Datum > ! hashgetbitmap(PG_FUNCTION_ARGS) > { > IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0); > ! TIDBitmap *tbm = (TIDBitmap *) PG_GETARG_POINTER(1); > HashScanOpaque so = (HashScanOpaque) scan->opaque; > bool res = true; > int32 ntids = 0; > > ! res = _hash_first(scan, ForwardScanDirection); > > ! while (res) > { > ! bool add_tuple; > /* > * Skip killed tuples if asked to. > */ > if (scan->ignore_killed_tuples) > { > ! Page page; > ! OffsetNumber offnum; > > ! offnum = ItemPointerGetOffsetNumber(&(so->hashso_curpos)); > ! page = BufferGetPage(so->hashso_curbuf); > ! add_tuple = !ItemIdDeleted(PageGetItemId(page, offnum)); > } > + else > + add_tuple = true; > > /* Save tuple ID, and continue scanning */ > ! if (add_tuple) > ! { > ! tbm_add_tuples(tbm, &scan->xs_ctup.t_self, 1, false); > ! ntids++; > ! } > > ! res = _hash_next(scan, ForwardScanDirection); > ! } > > ! PG_RETURN_INT32(ntids); > } > > > diff -c -N -r ./src/backend/access/index/indexam.c ../pgsql.new/src/backend/access/index/indexam.c > *** ./src/backend/access/index/indexam.c 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/backend/access/index/indexam.c 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 21,27 **** > * index_markpos - mark a scan position > * index_restrpos - restore a scan position > * index_getnext - get the next tuple from a scan > ! * index_getmulti - get multiple tuples from a scan > * index_bulk_delete - bulk deletion of index tuples > * index_vacuum_cleanup - post-deletion cleanup of an index > * index_getprocid - get a support procedure OID > --- 21,27 ---- > * index_markpos - mark a scan position > * index_restrpos - restore a scan position > * index_getnext - get the next tuple from a scan > ! * index_getbitmap - get all tuples from a scan > * index_bulk_delete - bulk deletion of index tuples > * index_vacuum_cleanup - post-deletion cleanup of an index > * index_getprocid - get a support procedure OID > *************** > *** 66,71 **** > --- 66,72 ---- > #include "access/heapam.h" > #include "pgstat.h" > #include "utils/relcache.h" > + #include "nodes/tidbitmap.h" > > > /* ---------------------------------------------------------------- > *************** > *** 506,549 **** > } > > /* ---------------- > ! * index_getmulti - get multiple tuples from an index scan > * > ! * Collects the TIDs of multiple heap tuples satisfying the scan keys. > * Since there's no interlock between the index scan and the eventual heap > * access, this is only safe to use with MVCC-based snapshots: the heap > * item slot could have been replaced by a newer tuple by the time we get > * to it. > * > ! * A TRUE result indicates more calls should occur; a FALSE result says the > ! * scan is done. *returned_tids could be zero or nonzero in either case. > * ---------------- > */ > ! bool > ! index_getmulti(IndexScanDesc scan, > ! ItemPointer tids, int32 max_tids, > ! int32 *returned_tids) > { > FmgrInfo *procedure; > ! bool found; > > SCAN_CHECKS; > ! GET_SCAN_PROCEDURE(amgetmulti); > > /* just make sure this is false... */ > scan->kill_prior_tuple = false; > > /* > ! * have the am's getmulti proc do all the work. > */ > ! found = DatumGetBool(FunctionCall4(procedure, > ! PointerGetDatum(scan), > ! PointerGetDatum(tids), > ! Int32GetDatum(max_tids), > ! PointerGetDatum(returned_tids))); > > ! pgstat_count_index_tuples(scan->indexRelation, *returned_tids); > > ! return found; > } > > /* ---------------- > --- 507,545 ---- > } > > /* ---------------- > ! * index_getbitmap - get all tuples at once from an index scan > * > ! * Adds the TIDs of all heap tuples satisfying the scan keys to a bitmap. > * Since there's no interlock between the index scan and the eventual heap > * access, this is only safe to use with MVCC-based snapshots: the heap > * item slot could have been replaced by a newer tuple by the time we get > * to it. > * > ! * Returns the number of matching tuples found. > * ---------------- > */ > ! int32 > ! index_getbitmap(IndexScanDesc scan, TIDBitmap *bitmap) > { > FmgrInfo *procedure; > ! int32 ntids; > > SCAN_CHECKS; > ! GET_SCAN_PROCEDURE(amgetbitmap); > > /* just make sure this is false... */ > scan->kill_prior_tuple = false; > > /* > ! * have the am's getbitmap proc do all the work. > */ > ! ntids = DatumGetInt32(FunctionCall2(procedure, > ! PointerGetDatum(scan), > ! PointerGetDatum(bitmap))); > > ! pgstat_count_index_tuples(scan->indexRelation, ntids); > > ! return ntids; > } > > /* ---------------- > diff -c -N -r ./src/backend/access/nbtree/nbtree.c ../pgsql.new/src/backend/access/nbtree/nbtree.c > *** ./src/backend/access/nbtree/nbtree.c 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/backend/access/nbtree/nbtree.c 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 278,302 **** > } > > /* > ! * btgetmulti() -- get multiple tuples at once > ! * > ! * In the current implementation there seems no strong reason to stop at > ! * index page boundaries; we just press on until we fill the caller's buffer > ! * or run out of matches. > */ > Datum > ! btgetmulti(PG_FUNCTION_ARGS) > { > IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0); > ! ItemPointer tids = (ItemPointer) PG_GETARG_POINTER(1); > ! int32 max_tids = PG_GETARG_INT32(2); > ! int32 *returned_tids = (int32 *) PG_GETARG_POINTER(3); > BTScanOpaque so = (BTScanOpaque) scan->opaque; > bool res = true; > int32 ntids = 0; > ! > ! if (max_tids <= 0) /* behave correctly in boundary case */ > ! PG_RETURN_BOOL(true); > > /* If we haven't started the scan yet, fetch the first page & tuple. */ > if (!BTScanPosIsValid(so->currPos)) > --- 278,294 ---- > } > > /* > ! * btgetbitmap() -- gets all matching tuples, and adds them to a bitmap > */ > Datum > ! btgetbitmap(PG_FUNCTION_ARGS) > { > IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0); > ! TIDBitmap *tbm = (TIDBitmap *) PG_GETARG_POINTER(1); > BTScanOpaque so = (BTScanOpaque) scan->opaque; > bool res = true; > int32 ntids = 0; > ! ItemPointer heapTid; > > /* If we haven't started the scan yet, fetch the first page & tuple. */ > if (!BTScanPosIsValid(so->currPos)) > *************** > *** 305,319 **** > if (!res) > { > /* empty scan */ > ! *returned_tids = ntids; > ! PG_RETURN_BOOL(res); > } > /* Save tuple ID, and continue scanning */ > ! tids[ntids] = scan->xs_ctup.t_self; > ntids++; > } > > ! while (ntids < max_tids) > { > /* > * Advance to next tuple within page. This is the same as the easy > --- 297,312 ---- > if (!res) > { > /* empty scan */ > ! PG_RETURN_INT32(0); > } > /* Save tuple ID, and continue scanning */ > ! heapTid = &scan->xs_ctup.t_self; > ! tbm_add_tuples(tbm, heapTid, 1, false); > ! > ntids++; > } > > ! while (true) > { > /* > * Advance to next tuple within page. This is the same as the easy > *************** > *** 328,339 **** > } > > /* Save tuple ID, and continue scanning */ > ! tids[ntids] = so->currPos.items[so->currPos.itemIndex].heapTid; > ntids++; > } > > ! *returned_tids = ntids; > ! PG_RETURN_BOOL(res); > } > > /* > --- 321,333 ---- > } > > /* Save tuple ID, and continue scanning */ > ! heapTid = &so->currPos.items[so->currPos.itemIndex].heapTid; > ! tbm_add_tuples(tbm, heapTid, 1, false); > ! > ntids++; > } > > ! PG_RETURN_INT32(ntids); > } > > /* > diff -c -N -r ./src/backend/executor/nodeBitmapHeapscan.c ../pgsql.new/src/backend/executor/nodeBitmapHeapscan.c > *** ./src/backend/executor/nodeBitmapHeapscan.c 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/backend/executor/nodeBitmapHeapscan.c 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 204,210 **** > * If we are using lossy info, we have to recheck the qual conditions > * at every tuple. > */ > ! if (tbmres->ntuples < 0) > { > econtext->ecxt_scantuple = slot; > ResetExprContext(econtext); > --- 204,210 ---- > * If we are using lossy info, we have to recheck the qual conditions > * at every tuple. > */ > ! if (tbmres->ntuples < 0 || tbmres->iscandidates) > { > econtext->ecxt_scantuple = slot; > ResetExprContext(econtext); > diff -c -N -r ./src/backend/executor/nodeBitmapIndexscan.c ../pgsql.new/src/backend/executor/nodeBitmapIndexscan.c > *** ./src/backend/executor/nodeBitmapIndexscan.c 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/backend/executor/nodeBitmapIndexscan.c 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 37,46 **** > Node * > MultiExecBitmapIndexScan(BitmapIndexScanState *node) > { > - #define MAX_TIDS 1024 > TIDBitmap *tbm; > IndexScanDesc scandesc; > - ItemPointerData tids[MAX_TIDS]; > int32 ntids; > double nTuples = 0; > bool doscan; > --- 37,44 ---- > *************** > *** 91,113 **** > */ > while (doscan) > { > ! bool more = index_getmulti(scandesc, tids, MAX_TIDS, &ntids); > > ! if (ntids > 0) > ! { > ! tbm_add_tuples(tbm, tids, ntids); > ! nTuples += ntids; > ! } > > CHECK_FOR_INTERRUPTS(); > > ! if (!more) > ! { > ! doscan = ExecIndexAdvanceArrayKeys(node->biss_ArrayKeys, > node->biss_NumArrayKeys); > ! if (doscan) /* reset index scan */ > ! index_rescan(node->biss_ScanDesc, node->biss_ScanKeys); > ! } > } > > /* must provide our own instrumentation support */ > --- 89,104 ---- > */ > while (doscan) > { > ! ntids = index_getbitmap(scandesc, tbm); > > ! nTuples += ntids; > > CHECK_FOR_INTERRUPTS(); > > ! doscan = ExecIndexAdvanceArrayKeys(node->biss_ArrayKeys, > node->biss_NumArrayKeys); > ! if (doscan) /* reset index scan */ > ! index_rescan(node->biss_ScanDesc, node->biss_ScanKeys); > } > > /* must provide our own instrumentation support */ > diff -c -N -r ./src/backend/nodes/tidbitmap.c ../pgsql.new/src/backend/nodes/tidbitmap.c > *** ./src/backend/nodes/tidbitmap.c 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/backend/nodes/tidbitmap.c 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 10,16 **** > * Also, since we wish to be able to store very large tuple sets in > * memory with this data structure, we support "lossy" storage, in which > * we no longer remember individual tuple offsets on a page but only the > ! * fact that a particular page needs to be visited. > * > * The "lossy" storage uses one bit per disk page, so at the standard 8K > * BLCKSZ, we can represent all pages in 64Gb of disk space in about 1Mb > --- 10,21 ---- > * Also, since we wish to be able to store very large tuple sets in > * memory with this data structure, we support "lossy" storage, in which > * we no longer remember individual tuple offsets on a page but only the > ! * fact that a particular page needs to be visited. We also support the > ! * notion of candidate matches, which are like non-lossy matches in that > ! * the individual tuple offsets are remembered, but the offsets remembered > ! * are a superset of the actual matches. Candidate matches need to be > ! * rechecked in the executor to see which ones really match. They are > ! * used when a lossy page is intersected with a non-lossy page. > * > * The "lossy" storage uses one bit per disk page, so at the standard 8K > * BLCKSZ, we can represent all pages in 64Gb of disk space in about 1Mb > *************** > *** 87,92 **** > --- 92,98 ---- > { > BlockNumber blockno; /* page number (hashtable key) */ > bool ischunk; /* T = lossy storage, F = exact */ > + bool iscandidate; /* should the results be rechecked? */ > bitmapword words[Max(WORDS_PER_PAGE, WORDS_PER_CHUNK)]; > } PagetableEntry; > > *************** > *** 145,150 **** > --- 151,160 ---- > static void tbm_lossify(TIDBitmap *tbm); > static int tbm_comparator(const void *left, const void *right); > > + #ifdef TIDBITMAP_DEBUG > + static void dump_pte(const PagetableEntry *e); > + static void tbm_dump(TIDBitmap *tbm); > + #endif > > /* > * tbm_create - create an initially-empty bitmap > *************** > *** 247,253 **** > * tbm_add_tuples - add some tuple IDs to a TIDBitmap > */ > void > ! tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids) > { > int i; > > --- 257,263 ---- > * tbm_add_tuples - add some tuple IDs to a TIDBitmap > */ > void > ! tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids, bool candidates) > { > int i; > > *************** > *** 281,286 **** > --- 291,297 ---- > bitnum = BITNUM(off - 1); > } > page->words[wordnum] |= ((bitmapword) 1 << bitnum); > + page->iscandidate = page->iscandidate || candidates; > > if (tbm->nentries > tbm->maxentries) > tbm_lossify(tbm); > *************** > *** 361,366 **** > --- 372,378 ---- > /* Both pages are exact, merge at the bit level */ > for (wordnum = 0; wordnum < WORDS_PER_PAGE; wordnum++) > apage->words[wordnum] |= bpage->words[wordnum]; > + apage->iscandidate = apage->iscandidate || bpage->iscandidate; > } > } > > *************** > *** 472,493 **** > else if (tbm_page_is_lossy(b, apage->blockno)) > { > /* > ! * When the page is lossy in b, we have to mark it lossy in a too. We > ! * know that no bits need be set in bitmap a, but we do not know which > ! * ones should be cleared, and we have no API for "at most these > ! * tuples need be checked". (Perhaps it's worth adding that?) > */ > ! tbm_mark_page_lossy(a, apage->blockno); > > - /* > - * Note: tbm_mark_page_lossy will have removed apage from a, and may > - * have inserted a new lossy chunk instead. We can continue the same > - * seq_search scan at the caller level, because it does not matter > - * whether we visit such a new chunk or not: it will have only the bit > - * for apage->blockno set, which is correct. > - * > - * We must return false here since apage was already deleted. > - */ > return false; > } > else > --- 484,496 ---- > else if (tbm_page_is_lossy(b, apage->blockno)) > { > /* > ! * Some of the tuples in 'a' might not satisfy the quals for 'b', > ! * but because the page 'b' is lossy, we don't know which ones. > ! * Therefore we mark 'a' as candidate to indicate that at most > ! * those tuples set in 'a' are matches. > */ > ! apage->iscandidate = true; > > return false; > } > else > *************** > *** 505,511 **** > --- 508,516 ---- > if (apage->words[wordnum] != 0) > candelete = false; > } > + apage->iscandidate = apage->iscandidate || bpage->iscandidate; > } > + > return candelete; > } > } > *************** > *** 677,682 **** > --- 682,688 ---- > } > output->blockno = page->blockno; > output->ntuples = ntuples; > + output->iscandidates = page->iscandidate; > tbm->spageptr++; > return output; > } > *************** > *** 936,938 **** > --- 942,994 ---- > return 1; > return 0; > } > + > + > + #ifdef TIDBITMAP_DEBUG > + static void > + dump_pte(const PagetableEntry *e) > + { > + int i; > + int max; > + char str[Max(WORDS_PER_PAGE, WORDS_PER_CHUNK) * BITS_PER_BITMAPWORD + 1]; > + > + if(e->ischunk) > + max = WORDS_PER_CHUNK * BITS_PER_BITMAPWORD; > + else > + max = WORDS_PER_PAGE * BITS_PER_BITMAPWORD; > + > + for(i=0; i < max; i++) > + { > + if(e->words[WORDNUM(i)] & (1<<(BITNUM(i)))) > + str[i] = '1'; > + else > + str[i] = '0'; > + } > + str[max] = '\0'; > + > + > + elog(LOG, "blockno %d%s%s: %s", e->blockno, > + e->ischunk ? " (lossy)" : "", > + e->iscandidate ? " (candidates)" : "", > + str); > + } > + > + > + static void > + tbm_dump(TIDBitmap *tbm) > + { > + int i; > + > + elog(LOG, "Bitmap, %d lossy and %d non-lossy pages", tbm->nchunks, tbm->npages); > + > + if(tbm->status == TBM_ONE_PAGE) > + dump_pte(&tbm->entry1); > + else > + { > + for(i = 0; i < tbm->nchunks; i++) > + dump_pte(tbm->schunks[i]); > + for(i = 0; i < tbm->npages; i++) > + dump_pte(tbm->spages[i]); > + } > + } > + #endif > diff -c -N -r ./src/include/access/genam.h ../pgsql.new/src/include/access/genam.h > *** ./src/include/access/genam.h 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/include/access/genam.h 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 17,22 **** > --- 17,23 ---- > #include "access/relscan.h" > #include "access/sdir.h" > #include "nodes/primnodes.h" > + #include "nodes/tidbitmap.h" > #include "storage/lock.h" > > /* > *************** > *** 109,117 **** > extern HeapTuple index_getnext(IndexScanDesc scan, ScanDirection direction); > extern bool index_getnext_indexitem(IndexScanDesc scan, > ScanDirection direction); > ! extern bool index_getmulti(IndexScanDesc scan, > ! ItemPointer tids, int32 max_tids, > ! int32 *returned_tids); > > extern IndexBulkDeleteResult *index_bulk_delete(IndexVacuumInfo *info, > IndexBulkDeleteResult *stats, > --- 110,116 ---- > extern HeapTuple index_getnext(IndexScanDesc scan, ScanDirection direction); > extern bool index_getnext_indexitem(IndexScanDesc scan, > ScanDirection direction); > ! extern int index_getbitmap(IndexScanDesc scan, TIDBitmap *bitmap); > > extern IndexBulkDeleteResult *index_bulk_delete(IndexVacuumInfo *info, > IndexBulkDeleteResult *stats, > diff -c -N -r ./src/include/access/gin.h ../pgsql.new/src/include/access/gin.h > *** ./src/include/access/gin.h 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/include/access/gin.h 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 421,427 **** > #define ItemPointerSetMin(p) ItemPointerSet( (p), (BlockNumber)0, (OffsetNumber)0) > #define ItemPointerIsMin(p) ( ItemPointerGetBlockNumber(p) == (BlockNumber)0 && ItemPointerGetOffsetNumber(p) == (OffsetNumber)0) > > ! extern Datum gingetmulti(PG_FUNCTION_ARGS); > extern Datum gingettuple(PG_FUNCTION_ARGS); > > /* ginvacuum.c */ > --- 421,427 ---- > #define ItemPointerSetMin(p) ItemPointerSet( (p), (BlockNumber)0, (OffsetNumber)0) > #define ItemPointerIsMin(p) ( ItemPointerGetBlockNumber(p) == (BlockNumber)0 && ItemPointerGetOffsetNumber(p) == (OffsetNumber)0) > > ! extern Datum gingetbitmap(PG_FUNCTION_ARGS); > extern Datum gingettuple(PG_FUNCTION_ARGS); > > /* ginvacuum.c */ > diff -c -N -r ./src/include/access/gist_private.h ../pgsql.new/src/include/access/gist_private.h > *** ./src/include/access/gist_private.h 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/include/access/gist_private.h 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 271,277 **** > > /* gistget.c */ > extern Datum gistgettuple(PG_FUNCTION_ARGS); > ! extern Datum gistgetmulti(PG_FUNCTION_ARGS); > > /* gistutil.c */ > > --- 271,277 ---- > > /* gistget.c */ > extern Datum gistgettuple(PG_FUNCTION_ARGS); > ! extern Datum gistgetbitmap(PG_FUNCTION_ARGS); > > /* gistutil.c */ > > diff -c -N -r ./src/include/access/hash.h ../pgsql.new/src/include/access/hash.h > *** ./src/include/access/hash.h 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/include/access/hash.h 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 233,239 **** > extern Datum hashinsert(PG_FUNCTION_ARGS); > extern Datum hashbeginscan(PG_FUNCTION_ARGS); > extern Datum hashgettuple(PG_FUNCTION_ARGS); > ! extern Datum hashgetmulti(PG_FUNCTION_ARGS); > extern Datum hashrescan(PG_FUNCTION_ARGS); > extern Datum hashendscan(PG_FUNCTION_ARGS); > extern Datum hashmarkpos(PG_FUNCTION_ARGS); > --- 233,239 ---- > extern Datum hashinsert(PG_FUNCTION_ARGS); > extern Datum hashbeginscan(PG_FUNCTION_ARGS); > extern Datum hashgettuple(PG_FUNCTION_ARGS); > ! extern Datum hashgetbitmap(PG_FUNCTION_ARGS); > extern Datum hashrescan(PG_FUNCTION_ARGS); > extern Datum hashendscan(PG_FUNCTION_ARGS); > extern Datum hashmarkpos(PG_FUNCTION_ARGS); > diff -c -N -r ./src/include/access/nbtree.h ../pgsql.new/src/include/access/nbtree.h > *** ./src/include/access/nbtree.h 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/include/access/nbtree.h 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 500,506 **** > extern Datum btinsert(PG_FUNCTION_ARGS); > extern Datum btbeginscan(PG_FUNCTION_ARGS); > extern Datum btgettuple(PG_FUNCTION_ARGS); > ! extern Datum btgetmulti(PG_FUNCTION_ARGS); > extern Datum btrescan(PG_FUNCTION_ARGS); > extern Datum btendscan(PG_FUNCTION_ARGS); > extern Datum btmarkpos(PG_FUNCTION_ARGS); > --- 500,506 ---- > extern Datum btinsert(PG_FUNCTION_ARGS); > extern Datum btbeginscan(PG_FUNCTION_ARGS); > extern Datum btgettuple(PG_FUNCTION_ARGS); > ! extern Datum btgetbitmap(PG_FUNCTION_ARGS); > extern Datum btrescan(PG_FUNCTION_ARGS); > extern Datum btendscan(PG_FUNCTION_ARGS); > extern Datum btmarkpos(PG_FUNCTION_ARGS); > diff -c -N -r ./src/include/catalog/pg_am.h ../pgsql.new/src/include/catalog/pg_am.h > *** ./src/include/catalog/pg_am.h 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/include/catalog/pg_am.h 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 56,62 **** > regproc aminsert; /* "insert this tuple" function */ > regproc ambeginscan; /* "start new scan" function */ > regproc amgettuple; /* "next valid tuple" function */ > ! regproc amgetmulti; /* "fetch multiple tuples" function */ > regproc amrescan; /* "restart this scan" function */ > regproc amendscan; /* "end this scan" function */ > regproc ammarkpos; /* "mark current scan position" function */ > --- 56,62 ---- > regproc aminsert; /* "insert this tuple" function */ > regproc ambeginscan; /* "start new scan" function */ > regproc amgettuple; /* "next valid tuple" function */ > ! regproc amgetbitmap; /* "fetch multiple tuples" function */ > regproc amrescan; /* "restart this scan" function */ > regproc amendscan; /* "end this scan" function */ > regproc ammarkpos; /* "mark current scan position" function */ > *************** > *** 94,100 **** > #define Anum_pg_am_aminsert 12 > #define Anum_pg_am_ambeginscan 13 > #define Anum_pg_am_amgettuple 14 > ! #define Anum_pg_am_amgetmulti 15 > #define Anum_pg_am_amrescan 16 > #define Anum_pg_am_amendscan 17 > #define Anum_pg_am_ammarkpos 18 > --- 94,100 ---- > #define Anum_pg_am_aminsert 12 > #define Anum_pg_am_ambeginscan 13 > #define Anum_pg_am_amgettuple 14 > ! #define Anum_pg_am_amgetbitmap 15 > #define Anum_pg_am_amrescan 16 > #define Anum_pg_am_amendscan 17 > #define Anum_pg_am_ammarkpos 18 > *************** > *** 110,125 **** > * ---------------- > */ > > ! DATA(insert OID = 403 ( btree 5 1 t t t t t t f t btinsert btbeginscan btgettuple btgetmulti btrescan btendscan btmarkposbtrestrpos btbuild btbulkdelete btvacuumcleanup btcostestimate btoptions )); > DESCR("b-tree index access method"); > #define BTREE_AM_OID 403 > ! DATA(insert OID = 405 ( hash 1 1 f f f f f f f f hashinsert hashbeginscan hashgettuple hashgetmulti hashrescan hashendscanhashmarkpos hashrestrpos hashbuild hashbulkdelete hashvacuumcleanup hashcostestimate hashoptions )); > DESCR("hash index access method"); > #define HASH_AM_OID 405 > ! DATA(insert OID = 783 ( gist 0 7 f f t t t t t t gistinsert gistbeginscan gistgettuple gistgetmulti gistrescan gistendscangistmarkpos gistrestrpos gistbuild gistbulkdelete gistvacuumcleanup gistcostestimate gistoptions )); > DESCR("GiST index access method"); > #define GIST_AM_OID 783 > ! DATA(insert OID = 2742 ( gin 0 4 f f f f f f t f gininsert ginbeginscan gingettuple gingetmulti ginrescan ginendscanginmarkpos ginrestrpos ginbuild ginbulkdelete ginvacuumcleanup gincostestimate ginoptions )); > DESCR("GIN index access method"); > #define GIN_AM_OID 2742 > > --- 110,125 ---- > * ---------------- > */ > > ! DATA(insert OID = 403 ( btree 5 1 t t t t t t f t btinsert btbeginscan btgettuple btgetbitmap btrescan btendscanbtmarkpos btrestrpos btbuild btbulkdelete btvacuumcleanup btcostestimate btoptions )); > DESCR("b-tree index access method"); > #define BTREE_AM_OID 403 > ! DATA(insert OID = 405 ( hash 1 1 f f f f f f f f hashinsert hashbeginscan hashgettuple hashgetbitmap hashrescan hashendscanhashmarkpos hashrestrpos hashbuild hashbulkdelete hashvacuumcleanup hashcostestimate hashoptions )); > DESCR("hash index access method"); > #define HASH_AM_OID 405 > ! DATA(insert OID = 783 ( gist 0 7 f f t t t t t t gistinsert gistbeginscan gistgettuple gistgetbitmap gistrescan gistendscangistmarkpos gistrestrpos gistbuild gistbulkdelete gistvacuumcleanup gistcostestimate gistoptions )); > DESCR("GiST index access method"); > #define GIST_AM_OID 783 > ! DATA(insert OID = 2742 ( gin 0 4 f f f f f f t f gininsert ginbeginscan gingettuple gingetbitmap ginrescan ginendscanginmarkpos ginrestrpos ginbuild ginbulkdelete ginvacuumcleanup gincostestimate ginoptions )); > DESCR("GIN index access method"); > #define GIN_AM_OID 2742 > > diff -c -N -r ./src/include/catalog/pg_proc.h ../pgsql.new/src/include/catalog/pg_proc.h > *** ./src/include/catalog/pg_proc.h 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/include/catalog/pg_proc.h 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 658,664 **** > > DATA(insert OID = 330 ( btgettuple PGNSP PGUID 12 1 0 f f t f v 2 16 "2281 2281" _null_ _null_ _null_ btgettuple- _null_ )); > DESCR("btree(internal)"); > ! DATA(insert OID = 636 ( btgetmulti PGNSP PGUID 12 1 0 f f t f v 4 16 "2281 2281 2281 2281" _null_ _null_ _null_ btgetmulti - _null_ )); > DESCR("btree(internal)"); > DATA(insert OID = 331 ( btinsert PGNSP PGUID 12 1 0 f f t f v 6 16 "2281 2281 2281 2281 2281 2281" _null__null_ _null_ btinsert - _null_ )); > DESCR("btree(internal)"); > --- 658,664 ---- > > DATA(insert OID = 330 ( btgettuple PGNSP PGUID 12 1 0 f f t f v 2 16 "2281 2281" _null_ _null_ _null_ btgettuple- _null_ )); > DESCR("btree(internal)"); > ! DATA(insert OID = 636 ( btgetbitmap PGNSP PGUID 12 1 0 f f t f v 4 16 "2281 2281 2281 2281" _null_ _null_ _null_ btgetbitmap - _null_ )); > DESCR("btree(internal)"); > DATA(insert OID = 331 ( btinsert PGNSP PGUID 12 1 0 f f t f v 6 16 "2281 2281 2281 2281 2281 2281" _null__null_ _null_ btinsert - _null_ )); > DESCR("btree(internal)"); > *************** > *** 777,783 **** > > DATA(insert OID = 440 ( hashgettuple PGNSP PGUID 12 1 0 f f t f v 2 16 "2281 2281" _null_ _null_ _null_ hashgettuple- _null_ )); > DESCR("hash(internal)"); > ! DATA(insert OID = 637 ( hashgetmulti PGNSP PGUID 12 1 0 f f t f v 4 16 "2281 2281 2281 2281" _null_ _null_ _null_ hashgetmulti - _null_ )); > DESCR("hash(internal)"); > DATA(insert OID = 441 ( hashinsert PGNSP PGUID 12 1 0 f f t f v 6 16 "2281 2281 2281 2281 2281 2281" _null__null_ _null_ hashinsert - _null_ )); > DESCR("hash(internal)"); > --- 777,783 ---- > > DATA(insert OID = 440 ( hashgettuple PGNSP PGUID 12 1 0 f f t f v 2 16 "2281 2281" _null_ _null_ _null_ hashgettuple- _null_ )); > DESCR("hash(internal)"); > ! DATA(insert OID = 637 ( hashgetbitmap PGNSP PGUID 12 1 0 f f t f v 4 16 "2281 2281 2281 2281" _null_ _null_ _null_ hashgetbitmap - _null_ )); > DESCR("hash(internal)"); > DATA(insert OID = 441 ( hashinsert PGNSP PGUID 12 1 0 f f t f v 6 16 "2281 2281 2281 2281 2281 2281" _null__null_ _null_ hashinsert - _null_ )); > DESCR("hash(internal)"); > *************** > *** 1045,1051 **** > > DATA(insert OID = 774 ( gistgettuple PGNSP PGUID 12 1 0 f f t f v 2 16 "2281 2281" _null_ _null_ _null_ gistgettuple- _null_ )); > DESCR("gist(internal)"); > ! DATA(insert OID = 638 ( gistgetmulti PGNSP PGUID 12 1 0 f f t f v 4 16 "2281 2281 2281 2281" _null_ _null_ _null_ gistgetmulti - _null_ )); > DESCR("gist(internal)"); > DATA(insert OID = 775 ( gistinsert PGNSP PGUID 12 1 0 f f t f v 6 16 "2281 2281 2281 2281 2281 2281" _null__null_ _null_ gistinsert - _null_ )); > DESCR("gist(internal)"); > --- 1045,1051 ---- > > DATA(insert OID = 774 ( gistgettuple PGNSP PGUID 12 1 0 f f t f v 2 16 "2281 2281" _null_ _null_ _null_ gistgettuple- _null_ )); > DESCR("gist(internal)"); > ! DATA(insert OID = 638 ( gistgetbitmap PGNSP PGUID 12 1 0 f f t f v 4 16 "2281 2281 2281 2281" _null_ _null_ _null_ gistgetbitmap - _null_ )); > DESCR("gist(internal)"); > DATA(insert OID = 775 ( gistinsert PGNSP PGUID 12 1 0 f f t f v 6 16 "2281 2281 2281 2281 2281 2281" _null__null_ _null_ gistinsert - _null_ )); > DESCR("gist(internal)"); > *************** > *** 3941,3947 **** > /* GIN */ > DATA(insert OID = 2730 ( gingettuple PGNSP PGUID 12 1 0 f f t f v 2 16 "2281 2281" _null_ _null_ _null_ gingettuple- _null_ )); > DESCR("gin(internal)"); > ! DATA(insert OID = 2731 ( gingetmulti PGNSP PGUID 12 1 0 f f t f v 4 16 "2281 2281 2281 2281" _null_ _null_ _null_ gingetmulti - _null_ )); > DESCR("gin(internal)"); > DATA(insert OID = 2732 ( gininsert PGNSP PGUID 12 1 0 f f t f v 6 16 "2281 2281 2281 2281 2281 2281" _null__null_ _null_ gininsert - _null_ )); > DESCR("gin(internal)"); > --- 3941,3947 ---- > /* GIN */ > DATA(insert OID = 2730 ( gingettuple PGNSP PGUID 12 1 0 f f t f v 2 16 "2281 2281" _null_ _null_ _null_ gingettuple- _null_ )); > DESCR("gin(internal)"); > ! DATA(insert OID = 2731 ( gingetbitmap PGNSP PGUID 12 1 0 f f t f v 4 16 "2281 2281 2281 2281" _null_ _null_ _null_ gingetbitmap - _null_ )); > DESCR("gin(internal)"); > DATA(insert OID = 2732 ( gininsert PGNSP PGUID 12 1 0 f f t f v 6 16 "2281 2281 2281 2281 2281 2281" _null__null_ _null_ gininsert - _null_ )); > DESCR("gin(internal)"); > diff -c -N -r ./src/include/nodes/tidbitmap.h ../pgsql.new/src/include/nodes/tidbitmap.h > *** ./src/include/nodes/tidbitmap.h 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/include/nodes/tidbitmap.h 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 36,41 **** > --- 36,42 ---- > { > BlockNumber blockno; /* page number containing tuples */ > int ntuples; /* -1 indicates lossy result */ > + bool iscandidates; /* do the results need to be rechecked */ > OffsetNumber offsets[1]; /* VARIABLE LENGTH ARRAY */ > } TBMIterateResult; /* VARIABLE LENGTH STRUCT */ > > *************** > *** 44,50 **** > extern TIDBitmap *tbm_create(long maxbytes); > extern void tbm_free(TIDBitmap *tbm); > > ! extern void tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids); > > extern void tbm_union(TIDBitmap *a, const TIDBitmap *b); > extern void tbm_intersect(TIDBitmap *a, const TIDBitmap *b); > --- 45,51 ---- > extern TIDBitmap *tbm_create(long maxbytes); > extern void tbm_free(TIDBitmap *tbm); > > ! extern void tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids, bool candidates); > > extern void tbm_union(TIDBitmap *a, const TIDBitmap *b); > extern void tbm_intersect(TIDBitmap *a, const TIDBitmap *b); > diff -c -N -r ./src/include/utils/rel.h ../pgsql.new/src/include/utils/rel.h > *** ./src/include/utils/rel.h 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/include/utils/rel.h 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 98,104 **** > FmgrInfo aminsert; > FmgrInfo ambeginscan; > FmgrInfo amgettuple; > ! FmgrInfo amgetmulti; > FmgrInfo amrescan; > FmgrInfo amendscan; > FmgrInfo ammarkpos; > --- 98,104 ---- > FmgrInfo aminsert; > FmgrInfo ambeginscan; > FmgrInfo amgettuple; > ! FmgrInfo amgetbitmap; > FmgrInfo amrescan; > FmgrInfo amendscan; > FmgrInfo ammarkpos; > diff -c -N -r ./src/test/regress/expected/bitmapops.out ../pgsql.new/src/test/regress/expected/bitmapops.out > *** ./src/test/regress/expected/bitmapops.out 1970-01-01 03:00:00.000000000 +0300 > --- ../pgsql.new/src/test/regress/expected/bitmapops.out 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 0 **** > --- 1,38 ---- > + -- Test bitmap AND and OR > + -- Generate enough data that we can test the lossy bitmaps. > + -- There's 55 tuples per page in the table. 53 is just > + -- below 55, so that an index scan with qual a = constant > + -- will return at least one hit per page. 59 is just above > + -- 55, so that an index scan with qual b = constant will return > + -- hits on most but not all pages. 53 and 59 are prime, so that > + -- there's a maximum number of a,b combinations in the table. > + -- That allows us to test all the different combinations of > + -- lossy and non-lossy pages with the minimum amount of data > + CREATE TABLE bmscantest (a int, b int, t text); > + INSERT INTO bmscantest > + SELECT (r%53), (r%59), 'foooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooo' > + FROM generate_series(1,70000) r; > + CREATE INDEX i_bmtest_a ON bmscantest(a); > + CREATE INDEX i_bmtest_b ON bmscantest(b); > + -- We want to use bitmapscans. With default settings, the planner currently > + -- chooses a bitmap scan for the queries below anyway, but let's make sure. > + set enable_indexscan=false; > + set enable_seqscan=false; > + -- Lower work_mem to trigger use of lossy bitmaps > + set work_mem = 64; > + -- Test bitmap-and. > + SELECT count(*) FROM bmscantest WHERE a = 1 AND b = 1; > + count > + ------- > + 23 > + (1 row) > + > + -- Test bitmap-or. > + SELECT count(*) FROM bmscantest WHERE a = 1 OR b = 1; > + count > + ------- > + 2485 > + (1 row) > + > + -- clean up > + DROP TABLE bmscantest; > diff -c -N -r ./src/test/regress/expected/create_index.out ../pgsql.new/src/test/regress/expected/create_index.out > *** ./src/test/regress/expected/create_index.out 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/test/regress/expected/create_index.out 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 327,332 **** > --- 327,420 ---- > 96 | {23,97,43} | {AAAAAAAAAA646,A87088} > (1 row) > > + -- Repeat some of the above tests but make sure we exercise bitmapscans > + SET enable_indexscan = OFF; > + SELECT * FROM array_index_op_test WHERE i @> '{32}' ORDER BY seqno; > + seqno | i | t > + -------+---------------------------------+------------------------------------------------------------------------------------------------------------------------------------ > + 6 | {39,35,5,94,17,92,60,32} | {AAAAAAAAAAAAAAA35875,AAAAAAAAAAAAAAAA23657} > + 74 | {32} | {AAAAAAAAAAAAAAAA1729,AAAAAAAAAAAAA22860,AAAAAA99807,AAAAA17383,AAAAAAAAAAAAAAA67062,AAAAAAAAAAA15165,AAAAAAAAAAA50956} > + 77 | {97,15,32,17,55,59,18,37,50,39} | {AAAAAAAAAAAA67946,AAAAAA54032,AAAAAAAA81587,55847,AAAAAAAAAAAAAA28620,AAAAAAAAAAAAAAAAA43052,AAAAAA75463,AAAA49534,AAAAAAAA44066} > + 89 | {40,32,17,6,30,88} | {AA44673,AAAAAAAAAAA6119,AAAAAAAAAAAAAAAA23657,AAAAAAAAAAAAAAAAAA47955,AAAAAAAAAAAAAAAA33598,AAAAAAAAAAA33576,AA44673} > + 98 | {38,34,32,89} | {AAAAAAAAAAAAAAAAAA71621,AAAA8857,AAAAAAAAAAAAAAAAAAA65037,AAAAAAAAAAAAAAAA31334,AAAAAAAAAA48845} > + 100 | {85,32,57,39,49,84,32,3,30} | {AAAAAAA80240,AAAAAAAAAAAAAAAA1729,AAAAA60038,AAAAAAAAAAA92631,AAAAAAAA9523} > + (6 rows) > + > + SELECT * FROM array_index_op_test WHERE i && '{32}' ORDER BY seqno; > + seqno | i | t > + -------+---------------------------------+------------------------------------------------------------------------------------------------------------------------------------ > + 6 | {39,35,5,94,17,92,60,32} | {AAAAAAAAAAAAAAA35875,AAAAAAAAAAAAAAAA23657} > + 74 | {32} | {AAAAAAAAAAAAAAAA1729,AAAAAAAAAAAAA22860,AAAAAA99807,AAAAA17383,AAAAAAAAAAAAAAA67062,AAAAAAAAAAA15165,AAAAAAAAAAA50956} > + 77 | {97,15,32,17,55,59,18,37,50,39} | {AAAAAAAAAAAA67946,AAAAAA54032,AAAAAAAA81587,55847,AAAAAAAAAAAAAA28620,AAAAAAAAAAAAAAAAA43052,AAAAAA75463,AAAA49534,AAAAAAAA44066} > + 89 | {40,32,17,6,30,88} | {AA44673,AAAAAAAAAAA6119,AAAAAAAAAAAAAAAA23657,AAAAAAAAAAAAAAAAAA47955,AAAAAAAAAAAAAAAA33598,AAAAAAAAAAA33576,AA44673} > + 98 | {38,34,32,89} | {AAAAAAAAAAAAAAAAAA71621,AAAA8857,AAAAAAAAAAAAAAAAAAA65037,AAAAAAAAAAAAAAAA31334,AAAAAAAAAA48845} > + 100 | {85,32,57,39,49,84,32,3,30} | {AAAAAAA80240,AAAAAAAAAAAAAAAA1729,AAAAA60038,AAAAAAAAAAA92631,AAAAAAAA9523} > + (6 rows) > + > + SELECT * FROM array_index_op_test WHERE i @> '{17}' ORDER BY seqno; > + seqno | i | t > + -------+---------------------------------+------------------------------------------------------------------------------------------------------------------------------------ > + 6 | {39,35,5,94,17,92,60,32} | {AAAAAAAAAAAAAAA35875,AAAAAAAAAAAAAAAA23657} > + 12 | {17,99,18,52,91,72,0,43,96,23} | {AAAAA33250,AAAAAAAAAAAAAAAAAAA85420,AAAAAAAAAAA33576} > + 15 | {17,14,16,63,67} | {AA6416,AAAAAAAAAA646,AAAAA95309} > + 19 | {52,82,17,74,23,46,69,51,75} | {AAAAAAAAAAAAA73084,AAAAA75968,AAAAAAAAAAAAAAAA14047,AAAAAAA80240,AAAAAAAAAAAAAAAAAAA1205,A68938} > + 53 | {38,17} | {AAAAAAAAAAA21658} > + 65 | {61,5,76,59,17} | {AAAAAA99807,AAAAA64741,AAAAAAAAAAA53908,AA21643,AAAAAAAAA10012} > + 77 | {97,15,32,17,55,59,18,37,50,39} | {AAAAAAAAAAAA67946,AAAAAA54032,AAAAAAAA81587,55847,AAAAAAAAAAAAAA28620,AAAAAAAAAAAAAAAAA43052,AAAAAA75463,AAAA49534,AAAAAAAA44066} > + 89 | {40,32,17,6,30,88} | {AA44673,AAAAAAAAAAA6119,AAAAAAAAAAAAAAAA23657,AAAAAAAAAAAAAAAAAA47955,AAAAAAAAAAAAAAAA33598,AAAAAAAAAAA33576,AA44673} > + (8 rows) > + > + SELECT * FROM array_index_op_test WHERE i && '{17}' ORDER BY seqno; > + seqno | i | t > + -------+---------------------------------+------------------------------------------------------------------------------------------------------------------------------------ > + 6 | {39,35,5,94,17,92,60,32} | {AAAAAAAAAAAAAAA35875,AAAAAAAAAAAAAAAA23657} > + 12 | {17,99,18,52,91,72,0,43,96,23} | {AAAAA33250,AAAAAAAAAAAAAAAAAAA85420,AAAAAAAAAAA33576} > + 15 | {17,14,16,63,67} | {AA6416,AAAAAAAAAA646,AAAAA95309} > + 19 | {52,82,17,74,23,46,69,51,75} | {AAAAAAAAAAAAA73084,AAAAA75968,AAAAAAAAAAAAAAAA14047,AAAAAAA80240,AAAAAAAAAAAAAAAAAAA1205,A68938} > + 53 | {38,17} | {AAAAAAAAAAA21658} > + 65 | {61,5,76,59,17} | {AAAAAA99807,AAAAA64741,AAAAAAAAAAA53908,AA21643,AAAAAAAAA10012} > + 77 | {97,15,32,17,55,59,18,37,50,39} | {AAAAAAAAAAAA67946,AAAAAA54032,AAAAAAAA81587,55847,AAAAAAAAAAAAAA28620,AAAAAAAAAAAAAAAAA43052,AAAAAA75463,AAAA49534,AAAAAAAA44066} > + 89 | {40,32,17,6,30,88} | {AA44673,AAAAAAAAAAA6119,AAAAAAAAAAAAAAAA23657,AAAAAAAAAAAAAAAAAA47955,AAAAAAAAAAAAAAAA33598,AAAAAAAAAAA33576,AA44673} > + (8 rows) > + > + SELECT * FROM array_index_op_test WHERE i @> '{32,17}' ORDER BY seqno; > + seqno | i | t > + -------+---------------------------------+------------------------------------------------------------------------------------------------------------------------------------ > + 6 | {39,35,5,94,17,92,60,32} | {AAAAAAAAAAAAAAA35875,AAAAAAAAAAAAAAAA23657} > + 77 | {97,15,32,17,55,59,18,37,50,39} | {AAAAAAAAAAAA67946,AAAAAA54032,AAAAAAAA81587,55847,AAAAAAAAAAAAAA28620,AAAAAAAAAAAAAAAAA43052,AAAAAA75463,AAAA49534,AAAAAAAA44066} > + 89 | {40,32,17,6,30,88} | {AA44673,AAAAAAAAAAA6119,AAAAAAAAAAAAAAAA23657,AAAAAAAAAAAAAAAAAA47955,AAAAAAAAAAAAAAAA33598,AAAAAAAAAAA33576,AA44673} > + (3 rows) > + > + SELECT * FROM array_index_op_test WHERE i && '{32,17}' ORDER BY seqno; > + seqno | i | t > + -------+---------------------------------+------------------------------------------------------------------------------------------------------------------------------------ > + 6 | {39,35,5,94,17,92,60,32} | {AAAAAAAAAAAAAAA35875,AAAAAAAAAAAAAAAA23657} > + 12 | {17,99,18,52,91,72,0,43,96,23} | {AAAAA33250,AAAAAAAAAAAAAAAAAAA85420,AAAAAAAAAAA33576} > + 15 | {17,14,16,63,67} | {AA6416,AAAAAAAAAA646,AAAAA95309} > + 19 | {52,82,17,74,23,46,69,51,75} | {AAAAAAAAAAAAA73084,AAAAA75968,AAAAAAAAAAAAAAAA14047,AAAAAAA80240,AAAAAAAAAAAAAAAAAAA1205,A68938} > + 53 | {38,17} | {AAAAAAAAAAA21658} > + 65 | {61,5,76,59,17} | {AAAAAA99807,AAAAA64741,AAAAAAAAAAA53908,AA21643,AAAAAAAAA10012} > + 74 | {32} | {AAAAAAAAAAAAAAAA1729,AAAAAAAAAAAAA22860,AAAAAA99807,AAAAA17383,AAAAAAAAAAAAAAA67062,AAAAAAAAAAA15165,AAAAAAAAAAA50956} > + 77 | {97,15,32,17,55,59,18,37,50,39} | {AAAAAAAAAAAA67946,AAAAAA54032,AAAAAAAA81587,55847,AAAAAAAAAAAAAA28620,AAAAAAAAAAAAAAAAA43052,AAAAAA75463,AAAA49534,AAAAAAAA44066} > + 89 | {40,32,17,6,30,88} | {AA44673,AAAAAAAAAAA6119,AAAAAAAAAAAAAAAA23657,AAAAAAAAAAAAAAAAAA47955,AAAAAAAAAAAAAAAA33598,AAAAAAAAAAA33576,AA44673} > + 98 | {38,34,32,89} | {AAAAAAAAAAAAAAAAAA71621,AAAA8857,AAAAAAAAAAAAAAAAAAA65037,AAAAAAAAAAAAAAAA31334,AAAAAAAAAA48845} > + 100 | {85,32,57,39,49,84,32,3,30} | {AAAAAAA80240,AAAAAAAAAAAAAAAA1729,AAAAA60038,AAAAAAAAAAA92631,AAAAAAAA9523} > + (11 rows) > + > + SELECT * FROM array_index_op_test WHERE i <@ '{38,34,32,89}' ORDER BY seqno; > + seqno | i | t > + -------+---------------+---------------------------------------------------------------------------------------------------------------------------- > + 40 | {34} | {AAAAAAAAAAAAAA10611,AAAAAAAAAAAAAAAAAAA1205,AAAAAAAAAAA50956,AAAAAAAAAAAAAAAA31334,AAAAA70466,AAAAAAAA81587,AAAAAAA74623} > + 74 | {32} | {AAAAAAAAAAAAAAAA1729,AAAAAAAAAAAAA22860,AAAAAA99807,AAAAA17383,AAAAAAAAAAAAAAA67062,AAAAAAAAAAA15165,AAAAAAAAAAA50956} > + 98 | {38,34,32,89} | {AAAAAAAAAAAAAAAAAA71621,AAAA8857,AAAAAAAAAAAAAAAAAAA65037,AAAAAAAAAAAAAAAA31334,AAAAAAAAAA48845} > + (3 rows) > + > + SELECT * FROM array_index_op_test WHERE i = '{47,77}' ORDER BY seqno; > + seqno | i | t > + -------+---------+----------------------------------------------------------------------------------------------------------------- > + 95 | {47,77} | {AAAAAAAAAAAAAAAAA764,AAAAAAAAAAA74076,AAAAAAAAAA18107,AAAAA40681,AAAAAAAAAAAAAAA35875,AAAAA60038,AAAAAAA56483} > + (1 row) > + > RESET enable_seqscan; > RESET enable_indexscan; > RESET enable_bitmapscan; > diff -c -N -r ./src/test/regress/expected/oidjoins.out ../pgsql.new/src/test/regress/expected/oidjoins.out > *** ./src/test/regress/expected/oidjoins.out 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/test/regress/expected/oidjoins.out 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 65,76 **** > ------+------------ > (0 rows) > > ! SELECT ctid, amgetmulti > FROM pg_catalog.pg_am fk > ! WHERE amgetmulti != 0 AND > ! NOT EXISTS(SELECT 1 FROM pg_catalog.pg_proc pk WHERE pk.oid = fk.amgetmulti); > ! ctid | amgetmulti > ! ------+------------ > (0 rows) > > SELECT ctid, amrescan > --- 65,76 ---- > ------+------------ > (0 rows) > > ! SELECT ctid, amgetbitmap > FROM pg_catalog.pg_am fk > ! WHERE amgetbitmap != 0 AND > ! NOT EXISTS(SELECT 1 FROM pg_catalog.pg_proc pk WHERE pk.oid = fk.amgetbitmap); > ! ctid | amgetbitmap > ! ------+------------- > (0 rows) > > SELECT ctid, amrescan > diff -c -N -r ./src/test/regress/parallel_schedule ../pgsql.new/src/test/regress/parallel_schedule > *** ./src/test/regress/parallel_schedule 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/test/regress/parallel_schedule 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 61,67 **** > # ---------- > # The fourth group of parallel test > # ---------- > ! test: select_into select_distinct select_distinct_on select_implicit select_having subselect union case join aggregatestransactions random portals arrays btree_index hash_index update namespace prepared_xacts delete > > test: privileges > test: misc > --- 61,67 ---- > # ---------- > # The fourth group of parallel test > # ---------- > ! test: select_into select_distinct select_distinct_on select_implicit select_having subselect union case join aggregatesbitmapops transactions random portals arrays btree_index hash_index update namespace prepared_xacts delete > > test: privileges > test: misc > diff -c -N -r ./src/test/regress/serial_schedule ../pgsql.new/src/test/regress/serial_schedule > *** ./src/test/regress/serial_schedule 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/test/regress/serial_schedule 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 69,74 **** > --- 69,75 ---- > test: case > test: join > test: aggregates > + test: bitmapops > test: transactions > ignore: random > test: random > diff -c -N -r ./src/test/regress/sql/bitmapops.sql ../pgsql.new/src/test/regress/sql/bitmapops.sql > *** ./src/test/regress/sql/bitmapops.sql 1970-01-01 03:00:00.000000000 +0300 > --- ../pgsql.new/src/test/regress/sql/bitmapops.sql 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 0 **** > --- 1,41 ---- > + -- Test bitmap AND and OR > + > + > + -- Generate enough data that we can test the lossy bitmaps. > + > + -- There's 55 tuples per page in the table. 53 is just > + -- below 55, so that an index scan with qual a = constant > + -- will return at least one hit per page. 59 is just above > + -- 55, so that an index scan with qual b = constant will return > + -- hits on most but not all pages. 53 and 59 are prime, so that > + -- there's a maximum number of a,b combinations in the table. > + -- That allows us to test all the different combinations of > + -- lossy and non-lossy pages with the minimum amount of data > + > + CREATE TABLE bmscantest (a int, b int, t text); > + > + INSERT INTO bmscantest > + SELECT (r%53), (r%59), 'foooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooo' > + FROM generate_series(1,70000) r; > + > + CREATE INDEX i_bmtest_a ON bmscantest(a); > + CREATE INDEX i_bmtest_b ON bmscantest(b); > + > + -- We want to use bitmapscans. With default settings, the planner currently > + -- chooses a bitmap scan for the queries below anyway, but let's make sure. > + set enable_indexscan=false; > + set enable_seqscan=false; > + > + -- Lower work_mem to trigger use of lossy bitmaps > + set work_mem = 64; > + > + > + -- Test bitmap-and. > + SELECT count(*) FROM bmscantest WHERE a = 1 AND b = 1; > + > + -- Test bitmap-or. > + SELECT count(*) FROM bmscantest WHERE a = 1 OR b = 1; > + > + > + -- clean up > + DROP TABLE bmscantest; > diff -c -N -r ./src/test/regress/sql/create_index.sql ../pgsql.new/src/test/regress/sql/create_index.sql > *** ./src/test/regress/sql/create_index.sql 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/test/regress/sql/create_index.sql 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 167,172 **** > --- 167,183 ---- > SELECT * FROM array_index_op_test WHERE t <@ '{AAAAAAAA72908,AAAAAAAAAAAAAAAAAAA17075,AA88409,AAAAAAAAAAAAAAAAAA36842,AAAAAAA48038,AAAAAAAAAAAAAA10611}'ORDER BY seqno; > SELECT * FROM array_index_op_test WHERE t = '{AAAAAAAAAA646,A87088}' ORDER BY seqno; > > + -- Repeat some of the above tests but make sure we exercise bitmapscans > + SET enable_indexscan = OFF; > + > + SELECT * FROM array_index_op_test WHERE i @> '{32}' ORDER BY seqno; > + SELECT * FROM array_index_op_test WHERE i && '{32}' ORDER BY seqno; > + SELECT * FROM array_index_op_test WHERE i @> '{17}' ORDER BY seqno; > + SELECT * FROM array_index_op_test WHERE i && '{17}' ORDER BY seqno; > + SELECT * FROM array_index_op_test WHERE i @> '{32,17}' ORDER BY seqno; > + SELECT * FROM array_index_op_test WHERE i && '{32,17}' ORDER BY seqno; > + SELECT * FROM array_index_op_test WHERE i <@ '{38,34,32,89}' ORDER BY seqno; > + SELECT * FROM array_index_op_test WHERE i = '{47,77}' ORDER BY seqno; > > RESET enable_seqscan; > RESET enable_indexscan; > diff -c -N -r ./src/test/regress/sql/oidjoins.sql ../pgsql.new/src/test/regress/sql/oidjoins.sql > *** ./src/test/regress/sql/oidjoins.sql 2007-06-19 14:37:49.000000000 +0300 > --- ../pgsql.new/src/test/regress/sql/oidjoins.sql 2007-06-19 14:41:46.000000000 +0300 > *************** > *** 33,42 **** > FROM pg_catalog.pg_am fk > WHERE amgettuple != 0 AND > NOT EXISTS(SELECT 1 FROM pg_catalog.pg_proc pk WHERE pk.oid = fk.amgettuple); > ! SELECT ctid, amgetmulti > FROM pg_catalog.pg_am fk > ! WHERE amgetmulti != 0 AND > ! NOT EXISTS(SELECT 1 FROM pg_catalog.pg_proc pk WHERE pk.oid = fk.amgetmulti); > SELECT ctid, amrescan > FROM pg_catalog.pg_am fk > WHERE amrescan != 0 AND > --- 33,42 ---- > FROM pg_catalog.pg_am fk > WHERE amgettuple != 0 AND > NOT EXISTS(SELECT 1 FROM pg_catalog.pg_proc pk WHERE pk.oid = fk.amgettuple); > ! SELECT ctid, amgetbitmap > FROM pg_catalog.pg_am fk > ! WHERE amgetbitmap != 0 AND > ! NOT EXISTS(SELECT 1 FROM pg_catalog.pg_proc pk WHERE pk.oid = fk.amgetbitmap); > SELECT ctid, amrescan > FROM pg_catalog.pg_am fk > WHERE amrescan != 0 AND > > > ------------------------------------------------------------------------ > > > ---------------------------(end of broadcast)--------------------------- > TIP 9: In versions below 8.0, the planner will ignore your desire to > choose an index scan if your joining column's datatypes do not > match -- === The PostgreSQL Company: Command Prompt, Inc. === Sales/Support: +1.503.667.4564 || 24x7/Emergency: +1.800.492.2240 Providing the most comprehensive PostgreSQL solutions since 1997 http://www.commandprompt.com/ Donate to the PostgreSQL Project: http://www.postgresql.org/about/donate PostgreSQL Replication: http://www.commandprompt.com/products/
pgsql-patches by date: