diff options
Diffstat (limited to 'src/backend/access')
| -rw-r--r-- | src/backend/access/nbtree/nbtree.c | 2 | ||||
| -rw-r--r-- | src/backend/access/nbtree/nbtsearch.c | 11 | ||||
| -rw-r--r-- | src/backend/access/nbtree/nbtutils.c | 72 | ||||
| -rw-r--r-- | src/backend/access/transam/xlog.c | 4 |
4 files changed, 55 insertions, 34 deletions
diff --git a/src/backend/access/nbtree/nbtree.c b/src/backend/access/nbtree/nbtree.c index 03a1d7b027a..fdff960c130 100644 --- a/src/backend/access/nbtree/nbtree.c +++ b/src/backend/access/nbtree/nbtree.c @@ -417,6 +417,8 @@ btrescan(IndexScanDesc scan, ScanKey scankey, int nscankeys, * way, so we might as well avoid wasting cycles on acquiring page LSNs. * * See nbtree/README section on making concurrent TID recycling safe. + * + * Note: so->dropPin should never change across rescans. */ so->dropPin = (!scan->xs_want_itup && IsMVCCSnapshot(scan->xs_snapshot) && diff --git a/src/backend/access/nbtree/nbtsearch.c b/src/backend/access/nbtree/nbtsearch.c index 070f14c8b91..36544ecfd58 100644 --- a/src/backend/access/nbtree/nbtsearch.c +++ b/src/backend/access/nbtree/nbtsearch.c @@ -2282,9 +2282,12 @@ _bt_readfirstpage(IndexScanDesc scan, OffsetNumber offnum, ScanDirection dir) * previously-saved right link or left link. lastcurrblkno is the page that * was current at the point where the blkno link was saved, which we use to * reason about concurrent page splits/page deletions during backwards scans. + * In the common case where seized=false, blkno is either so->currPos.nextPage + * or so->currPos.prevPage, and lastcurrblkno is so->currPos.currPage. * - * On entry, caller shouldn't hold any locks or pins on any page (we work - * directly off of blkno and lastcurrblkno instead). Parallel scan callers + * On entry, so->currPos shouldn't be locked by caller. so->currPos.buf must + * be InvalidBuffer/unpinned as needed by caller (note that lastcurrblkno + * won't need to be read again in almost all cases). Parallel scan callers * that seized the scan before calling here should pass seized=true; such a * caller's blkno and lastcurrblkno arguments come from the seized scan. * seized=false callers just pass us the blkno/lastcurrblkno taken from their @@ -2301,8 +2304,8 @@ _bt_readfirstpage(IndexScanDesc scan, OffsetNumber offnum, ScanDirection dir) * success exit (except during so->dropPin index scans, when we drop the pin * eagerly to avoid blocking VACUUM). * - * If there are no more matching records in the given direction, we drop all - * locks and pins, invalidate so->currPos, and return false. + * If there are no more matching records in the given direction, we invalidate + * so->currPos (while ensuring it retains no locks or pins), and return false. * * We always release the scan for a parallel scan caller, regardless of * success or failure; we'll call _bt_parallel_release as soon as possible. diff --git a/src/backend/access/nbtree/nbtutils.c b/src/backend/access/nbtree/nbtutils.c index 29f0dca1b08..c71d1b6f2e1 100644 --- a/src/backend/access/nbtree/nbtutils.c +++ b/src/backend/access/nbtree/nbtutils.c @@ -63,7 +63,7 @@ static bool _bt_check_compare(IndexScanDesc scan, ScanDirection dir, bool *continuescan, int *ikey); static bool _bt_check_rowcompare(ScanKey skey, IndexTuple tuple, int tupnatts, TupleDesc tupdesc, - ScanDirection dir, bool *continuescan); + ScanDirection dir, bool forcenonrequired, bool *continuescan); static void _bt_checkkeys_look_ahead(IndexScanDesc scan, BTReadPageState *pstate, int tupnatts, TupleDesc tupdesc); static int _bt_keep_natts(Relation rel, IndexTuple lastleft, @@ -2902,10 +2902,8 @@ _bt_check_compare(IndexScanDesc scan, ScanDirection dir, /* row-comparison keys need special processing */ if (key->sk_flags & SK_ROW_HEADER) { - Assert(!forcenonrequired); /* forbidden by _bt_set_startikey */ - if (_bt_check_rowcompare(key, tuple, tupnatts, tupdesc, dir, - continuescan)) + forcenonrequired, continuescan)) continue; return false; } @@ -3062,7 +3060,8 @@ _bt_check_compare(IndexScanDesc scan, ScanDirection dir, */ static bool _bt_check_rowcompare(ScanKey skey, IndexTuple tuple, int tupnatts, - TupleDesc tupdesc, ScanDirection dir, bool *continuescan) + TupleDesc tupdesc, ScanDirection dir, + bool forcenonrequired, bool *continuescan) { ScanKey subkey = (ScanKey) DatumGetPointer(skey->sk_argument); int32 cmpresult = 0; @@ -3102,7 +3101,11 @@ _bt_check_rowcompare(ScanKey skey, IndexTuple tuple, int tupnatts, if (isNull) { - if (subkey->sk_flags & SK_BT_NULLS_FIRST) + if (forcenonrequired) + { + /* treating scan's keys as non-required */ + } + else if (subkey->sk_flags & SK_BT_NULLS_FIRST) { /* * Since NULLs are sorted before non-NULLs, we know we have @@ -3156,8 +3159,12 @@ _bt_check_rowcompare(ScanKey skey, IndexTuple tuple, int tupnatts, */ Assert(subkey != (ScanKey) DatumGetPointer(skey->sk_argument)); subkey--; - if ((subkey->sk_flags & SK_BT_REQFWD) && - ScanDirectionIsForward(dir)) + if (forcenonrequired) + { + /* treating scan's keys as non-required */ + } + else if ((subkey->sk_flags & SK_BT_REQFWD) && + ScanDirectionIsForward(dir)) *continuescan = false; else if ((subkey->sk_flags & SK_BT_REQBKWD) && ScanDirectionIsBackward(dir)) @@ -3209,7 +3216,7 @@ _bt_check_rowcompare(ScanKey skey, IndexTuple tuple, int tupnatts, break; } - if (!result) + if (!result && !forcenonrequired) { /* * Tuple fails this qual. If it's a required qual for the current @@ -3323,24 +3330,26 @@ _bt_checkkeys_look_ahead(IndexScanDesc scan, BTReadPageState *pstate, * current page and killed tuples thereon (generally, this should only be * called if so->numKilled > 0). * - * The caller does not have a lock on the page and may or may not have the - * page pinned in a buffer. Note that read-lock is sufficient for setting - * LP_DEAD status (which is only a hint). - * - * We match items by heap TID before assuming they are the right ones to - * delete. We cope with cases where items have moved right due to insertions. - * If an item has moved off the current page due to a split, we'll fail to - * find it and do nothing (this is not an error case --- we assume the item - * will eventually get marked in a future indexscan). + * Caller should not have a lock on the so->currPos page, but must hold a + * buffer pin when !so->dropPin. When we return, it still won't be locked. + * It'll continue to hold whatever pins were held before calling here. * - * Note that if we hold a pin on the target page continuously from initially - * reading the items until applying this function, VACUUM cannot have deleted - * any items on the page, so the page's TIDs can't have been recycled by now. - * There's no risk that we'll confuse a new index tuple that happens to use a - * recycled TID with a now-removed tuple with the same TID (that used to be on - * this same page). We can't rely on that during scans that drop pins eagerly + * We match items by heap TID before assuming they are the right ones to set + * LP_DEAD. If the scan is one that holds a buffer pin on the target page + * continuously from initially reading the items until applying this function + * (if it is a !so->dropPin scan), VACUUM cannot have deleted any items on the + * page, so the page's TIDs can't have been recycled by now. There's no risk + * that we'll confuse a new index tuple that happens to use a recycled TID + * with a now-removed tuple with the same TID (that used to be on this same + * page). We can't rely on that during scans that drop buffer pins eagerly * (so->dropPin scans), though, so we must condition setting LP_DEAD bits on * the page LSN having not changed since back when _bt_readpage saw the page. + * We totally give up on setting LP_DEAD bits when the page LSN changed. + * + * We give up much less often during !so->dropPin scans, but it still happens. + * We cope with cases where items have moved right due to insertions. If an + * item has moved off the current page due to a split, we'll fail to find it + * and just give up on it. */ void _bt_killitems(IndexScanDesc scan) @@ -3353,6 +3362,7 @@ _bt_killitems(IndexScanDesc scan) OffsetNumber maxoff; int numKilled = so->numKilled; bool killedsomething = false; + Buffer buf; Assert(numKilled > 0); Assert(BTScanPosIsValid(so->currPos)); @@ -3369,11 +3379,11 @@ _bt_killitems(IndexScanDesc scan) * concurrent VACUUMs from recycling any of the TIDs on the page. */ Assert(BTScanPosIsPinned(so->currPos)); - _bt_lockbuf(rel, so->currPos.buf, BT_READ); + buf = so->currPos.buf; + _bt_lockbuf(rel, buf, BT_READ); } else { - Buffer buf; XLogRecPtr latestlsn; Assert(!BTScanPosIsPinned(so->currPos)); @@ -3391,10 +3401,9 @@ _bt_killitems(IndexScanDesc scan) } /* Unmodified, hinting is safe */ - so->currPos.buf = buf; } - page = BufferGetPage(so->currPos.buf); + page = BufferGetPage(buf); opaque = BTPageGetOpaque(page); minoff = P_FIRSTDATAKEY(opaque); maxoff = PageGetMaxOffsetNumber(page); @@ -3511,10 +3520,13 @@ _bt_killitems(IndexScanDesc scan) if (killedsomething) { opaque->btpo_flags |= BTP_HAS_GARBAGE; - MarkBufferDirtyHint(so->currPos.buf, true); + MarkBufferDirtyHint(buf, true); } - _bt_unlockbuf(rel, so->currPos.buf); + if (!so->dropPin) + _bt_unlockbuf(rel, buf); + else + _bt_relbuf(rel, buf); } diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index 1914859b2ee..47ffc0a2307 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -7498,6 +7498,10 @@ CreateCheckPoint(int flags) if (PriorRedoPtr != InvalidXLogRecPtr) UpdateCheckPointDistanceEstimate(RedoRecPtr - PriorRedoPtr); +#ifdef USE_INJECTION_POINTS + INJECTION_POINT("checkpoint-before-old-wal-removal", NULL); +#endif + /* * Delete old log files, those no longer needed for last checkpoint to * prevent the disk holding the xlog from growing full. |