From b6cb833a6fd4d4e0c87d3e4e3fce30910eba874a Mon Sep 17 00:00:00 2001 From: Alexander Korotkov Date: Sun, 2 Apr 2023 03:26:35 +0300 Subject: [PATCH v4 1/2] Revise changes in 764da7710b and 11470f544e The mentioned commits evade extra tuple re-fetching and allow locking last versions of updated tuples in tuple_update() and tuple_delete(). This commit improves the things in the following ways. * tuple_update() and tuple_delete() can now fetch the old tuple version not only after lock, but also after successful UPDATE/DELETE. * Avoid tuple re-fetching in more general case including after row triggers. * Improve code API in heap_lock_tuple. Automatically detect prefetched tuple in slot to avoid the extra work on reading the buffer. * Remove LazyTupleTableSlot. It seems unreasonable complication for evading slot allocation, which is quite cheap. Reported-by: Andres Freund Discussion: https://postgr.es/m/20230323003003.plgaxjqahjgkuxrk%40awork3.anarazel.de --- src/backend/access/heap/heapam.c | 205 +++++++++++++----- src/backend/access/heap/heapam_handler.c | 143 +++++-------- src/backend/access/table/tableam.c | 24 ++- src/backend/commands/trigger.c | 55 ++--- src/backend/executor/execReplication.c | 19 +- src/backend/executor/nodeModifyTable.c | 253 +++++++++-------------- src/include/access/heapam.h | 19 +- src/include/access/tableam.h | 67 ++++-- src/include/commands/trigger.h | 4 +- src/include/executor/tuptable.h | 38 ---- src/tools/pgindent/typedefs.list | 2 - 11 files changed, 418 insertions(+), 411 deletions(-) diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c index f7d9ce59a47..3f1f23997fb 100644 --- a/src/backend/access/heap/heapam.c +++ b/src/backend/access/heap/heapam.c @@ -2449,10 +2449,11 @@ xmax_infomask_changed(uint16 new_infomask, uint16 old_infomask) } /* - * heap_delete - delete a tuple + * heap_delete - delete a tuple, optionally fetching it into a slot * * See table_tuple_delete() for an explanation of the parameters, except that - * this routine directly takes a tuple rather than a slot. + * this routine directly takes a tuple rather than a slot. Also, we don't + * place a lock on the tuple in this function, just fetch the existing version. * * In the failure cases, the routine fills *tmfd with the tuple's t_ctid, * t_xmax (resolving a possible MultiXact, if necessary), and t_cmax (the last @@ -2461,8 +2462,9 @@ xmax_infomask_changed(uint16 new_infomask, uint16 old_infomask) */ TM_Result heap_delete(Relation relation, ItemPointer tid, - CommandId cid, Snapshot crosscheck, bool wait, - TM_FailureData *tmfd, bool changingPart) + CommandId cid, Snapshot crosscheck, int options, + TM_FailureData *tmfd, bool changingPart, + TupleTableSlot *oldSlot) { TM_Result result; TransactionId xid = GetCurrentTransactionId(); @@ -2540,7 +2542,7 @@ l1: (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("attempted to delete invisible tuple"))); } - else if (result == TM_BeingModified && wait) + else if (result == TM_BeingModified && (options & TABLE_MODIFY_WAIT)) { TransactionId xwait; uint16 infomask; @@ -2676,7 +2678,30 @@ l1: tmfd->cmax = HeapTupleHeaderGetCmax(tp.t_data); else tmfd->cmax = InvalidCommandId; - UnlockReleaseBuffer(buffer); + + /* + * If we're asked to lock the updated tuple, we just fetch the + * existing tuple. That let's the caller save some resources on + * placing the lock. + */ + if (result == TM_Updated && + (options & TABLE_MODIFY_LOCK_UPDATED)) + { + BufferHeapTupleTableSlot *bslot; + + Assert(TTS_IS_BUFFERTUPLE(oldSlot)); + bslot = (BufferHeapTupleTableSlot *) oldSlot; + + LockBuffer(buffer, BUFFER_LOCK_UNLOCK); + bslot->base.tupdata = tp; + ExecStorePinnedBufferHeapTuple(&bslot->base.tupdata, + oldSlot, + buffer); + } + else + { + UnlockReleaseBuffer(buffer); + } if (have_tuple_lock) UnlockTupleTuplock(relation, &(tp.t_self), LockTupleExclusive); if (vmbuffer != InvalidBuffer) @@ -2850,8 +2875,24 @@ l1: */ CacheInvalidateHeapTuple(relation, &tp, NULL); - /* Now we can release the buffer */ - ReleaseBuffer(buffer); + /* Fetch the old tuple version if we're asked for that. */ + if (options & TABLE_MODIFY_FETCH_OLD_TUPLE) + { + BufferHeapTupleTableSlot *bslot; + + Assert(TTS_IS_BUFFERTUPLE(oldSlot)); + bslot = (BufferHeapTupleTableSlot *) oldSlot; + + bslot->base.tupdata = tp; + ExecStorePinnedBufferHeapTuple(&bslot->base.tupdata, + oldSlot, + buffer); + } + else + { + /* Now we can release the buffer */ + ReleaseBuffer(buffer); + } /* * Release the lmgr tuple lock, if we had it. @@ -2883,8 +2924,8 @@ simple_heap_delete(Relation relation, ItemPointer tid) result = heap_delete(relation, tid, GetCurrentCommandId(true), InvalidSnapshot, - true /* wait for commit */ , - &tmfd, false /* changingPart */ ); + TABLE_MODIFY_WAIT /* wait for commit */ , + &tmfd, false /* changingPart */ , NULL); switch (result) { case TM_SelfModified: @@ -2911,10 +2952,11 @@ simple_heap_delete(Relation relation, ItemPointer tid) } /* - * heap_update - replace a tuple + * heap_update - replace a tuple, optionally fetching it into a slot * * See table_tuple_update() for an explanation of the parameters, except that - * this routine directly takes a tuple rather than a slot. + * this routine directly takes a tuple rather than a slot. Also, we don't + * place a lock on the tuple in this function, just fetch the existing version. * * In the failure cases, the routine fills *tmfd with the tuple's t_ctid, * t_xmax (resolving a possible MultiXact, if necessary), and t_cmax (the last @@ -2923,9 +2965,9 @@ simple_heap_delete(Relation relation, ItemPointer tid) */ TM_Result heap_update(Relation relation, ItemPointer otid, HeapTuple newtup, - CommandId cid, Snapshot crosscheck, bool wait, + CommandId cid, Snapshot crosscheck, int options, TM_FailureData *tmfd, LockTupleMode *lockmode, - TU_UpdateIndexes *update_indexes) + TU_UpdateIndexes *update_indexes, TupleTableSlot *oldSlot) { TM_Result result; TransactionId xid = GetCurrentTransactionId(); @@ -3102,7 +3144,7 @@ l2: result = HeapTupleSatisfiesUpdate(&oldtup, cid, buffer); /* see below about the "no wait" case */ - Assert(result != TM_BeingModified || wait); + Assert(result != TM_BeingModified || (options & TABLE_MODIFY_WAIT)); if (result == TM_Invisible) { @@ -3111,7 +3153,7 @@ l2: (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("attempted to update invisible tuple"))); } - else if (result == TM_BeingModified && wait) + else if (result == TM_BeingModified && (options & TABLE_MODIFY_WAIT)) { TransactionId xwait; uint16 infomask; @@ -3313,7 +3355,30 @@ l2: tmfd->cmax = HeapTupleHeaderGetCmax(oldtup.t_data); else tmfd->cmax = InvalidCommandId; - UnlockReleaseBuffer(buffer); + + /* + * If we're asked to lock the updated tuple, we just fetch the + * existing tuple. That let's the caller save some resouces on + * placing the lock. + */ + if (result == TM_Updated && + (options & TABLE_MODIFY_LOCK_UPDATED)) + { + BufferHeapTupleTableSlot *bslot; + + Assert(TTS_IS_BUFFERTUPLE(oldSlot)); + bslot = (BufferHeapTupleTableSlot *) oldSlot; + + LockBuffer(buffer, BUFFER_LOCK_UNLOCK); + bslot->base.tupdata = oldtup; + ExecStorePinnedBufferHeapTuple(&bslot->base.tupdata, + oldSlot, + buffer); + } + else + { + UnlockReleaseBuffer(buffer); + } if (have_tuple_lock) UnlockTupleTuplock(relation, &(oldtup.t_self), *lockmode); if (vmbuffer != InvalidBuffer) @@ -3791,7 +3856,26 @@ l2: /* Now we can release the buffer(s) */ if (newbuf != buffer) ReleaseBuffer(newbuf); - ReleaseBuffer(buffer); + + /* Fetch the old tuple version if we're asked for that. */ + if (options & TABLE_MODIFY_FETCH_OLD_TUPLE) + { + BufferHeapTupleTableSlot *bslot; + + Assert(TTS_IS_BUFFERTUPLE(oldSlot)); + bslot = (BufferHeapTupleTableSlot *) oldSlot; + + bslot->base.tupdata = oldtup; + ExecStorePinnedBufferHeapTuple(&bslot->base.tupdata, + oldSlot, + buffer); + } + else + { + /* Now we can release the buffer */ + ReleaseBuffer(buffer); + } + if (BufferIsValid(vmbuffer_new)) ReleaseBuffer(vmbuffer_new); if (BufferIsValid(vmbuffer)) @@ -3999,8 +4083,8 @@ simple_heap_update(Relation relation, ItemPointer otid, HeapTuple tup, result = heap_update(relation, otid, tup, GetCurrentCommandId(true), InvalidSnapshot, - true /* wait for commit */ , - &tmfd, &lockmode, update_indexes); + TABLE_MODIFY_WAIT /* wait for commit */ , + &tmfd, &lockmode, update_indexes, NULL); switch (result) { case TM_SelfModified: @@ -4063,12 +4147,14 @@ get_mxact_status_for_lock(LockTupleMode mode, bool is_update) * tuples. * * Output parameters: - * *tuple: all fields filled in - * *buffer: set to buffer holding tuple (pinned but not locked at exit) + * *slot: BufferHeapTupleTableSlot filled with tuple * *tmfd: filled in failure cases (see below) * * Function results are the same as the ones for table_tuple_lock(). * + * If *slot already contains the target tuple, it takes advantage on that by + * skipping the ReadBuffer() call. + * * In the failure cases other than TM_Invisible, the routine fills * *tmfd with the tuple's t_ctid, t_xmax (resolving a possible MultiXact, * if necessary), and t_cmax (the last only for TM_SelfModified, @@ -4079,15 +4165,14 @@ get_mxact_status_for_lock(LockTupleMode mode, bool is_update) * See README.tuplock for a thorough explanation of this mechanism. */ TM_Result -heap_lock_tuple(Relation relation, HeapTuple tuple, +heap_lock_tuple(Relation relation, ItemPointer tid, TupleTableSlot *slot, CommandId cid, LockTupleMode mode, LockWaitPolicy wait_policy, - bool follow_updates, - Buffer *buffer, TM_FailureData *tmfd) + bool follow_updates, TM_FailureData *tmfd) { TM_Result result; - ItemPointer tid = &(tuple->t_self); ItemId lp; Page page; + Buffer buffer; Buffer vmbuffer = InvalidBuffer; BlockNumber block; TransactionId xid, @@ -4099,8 +4184,24 @@ heap_lock_tuple(Relation relation, HeapTuple tuple, bool skip_tuple_lock = false; bool have_tuple_lock = false; bool cleared_all_frozen = false; + BufferHeapTupleTableSlot *bslot = (BufferHeapTupleTableSlot *) slot; + HeapTuple tuple = &bslot->base.tupdata; + + Assert(TTS_IS_BUFFERTUPLE(slot)); - *buffer = ReadBuffer(relation, ItemPointerGetBlockNumber(tid)); + /* Take advantage if slot already contains the relevant tuple */ + if (!TTS_EMPTY(slot) && + slot->tts_tableOid == relation->rd_id && + ItemPointerCompare(&slot->tts_tid, tid) == 0 && + BufferIsValid(bslot->buffer)) + { + buffer = bslot->buffer; + IncrBufferRefCount(buffer); + } + else + { + buffer = ReadBuffer(relation, ItemPointerGetBlockNumber(tid)); + } block = ItemPointerGetBlockNumber(tid); /* @@ -4109,21 +4210,22 @@ heap_lock_tuple(Relation relation, HeapTuple tuple, * in the middle of changing this, so we'll need to recheck after we have * the lock. */ - if (PageIsAllVisible(BufferGetPage(*buffer))) + if (PageIsAllVisible(BufferGetPage(buffer))) visibilitymap_pin(relation, block, &vmbuffer); - LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); - page = BufferGetPage(*buffer); + page = BufferGetPage(buffer); lp = PageGetItemId(page, ItemPointerGetOffsetNumber(tid)); Assert(ItemIdIsNormal(lp)); + tuple->t_self = *tid; tuple->t_data = (HeapTupleHeader) PageGetItem(page, lp); tuple->t_len = ItemIdGetLength(lp); tuple->t_tableOid = RelationGetRelid(relation); l3: - result = HeapTupleSatisfiesUpdate(tuple, cid, *buffer); + result = HeapTupleSatisfiesUpdate(tuple, cid, buffer); if (result == TM_Invisible) { @@ -4152,7 +4254,7 @@ l3: infomask2 = tuple->t_data->t_infomask2; ItemPointerCopy(&tuple->t_data->t_ctid, &t_ctid); - LockBuffer(*buffer, BUFFER_LOCK_UNLOCK); + LockBuffer(buffer, BUFFER_LOCK_UNLOCK); /* * If any subtransaction of the current top transaction already holds @@ -4304,12 +4406,12 @@ l3: { result = res; /* recovery code expects to have buffer lock held */ - LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); goto failed; } } - LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); /* * Make sure it's still an appropriate lock, else start over. @@ -4344,7 +4446,7 @@ l3: if (HEAP_XMAX_IS_LOCKED_ONLY(infomask) && !HEAP_XMAX_IS_EXCL_LOCKED(infomask)) { - LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); /* * Make sure it's still an appropriate lock, else start over. @@ -4372,7 +4474,7 @@ l3: * No conflict, but if the xmax changed under us in the * meantime, start over. */ - LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); if (xmax_infomask_changed(tuple->t_data->t_infomask, infomask) || !TransactionIdEquals(HeapTupleHeaderGetRawXmax(tuple->t_data), xwait)) @@ -4384,7 +4486,7 @@ l3: } else if (HEAP_XMAX_IS_KEYSHR_LOCKED(infomask)) { - LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); /* if the xmax changed in the meantime, start over */ if (xmax_infomask_changed(tuple->t_data->t_infomask, infomask) || @@ -4412,7 +4514,7 @@ l3: TransactionIdIsCurrentTransactionId(xwait)) { /* ... but if the xmax changed in the meantime, start over */ - LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); if (xmax_infomask_changed(tuple->t_data->t_infomask, infomask) || !TransactionIdEquals(HeapTupleHeaderGetRawXmax(tuple->t_data), xwait)) @@ -4434,7 +4536,7 @@ l3: */ if (require_sleep && (result == TM_Updated || result == TM_Deleted)) { - LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); goto failed; } else if (require_sleep) @@ -4459,7 +4561,7 @@ l3: */ result = TM_WouldBlock; /* recovery code expects to have buffer lock held */ - LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); goto failed; } @@ -4485,7 +4587,7 @@ l3: { result = TM_WouldBlock; /* recovery code expects to have buffer lock held */ - LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); goto failed; } break; @@ -4525,7 +4627,7 @@ l3: { result = TM_WouldBlock; /* recovery code expects to have buffer lock held */ - LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); goto failed; } break; @@ -4551,12 +4653,12 @@ l3: { result = res; /* recovery code expects to have buffer lock held */ - LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); goto failed; } } - LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); /* * xwait is done, but if xwait had just locked the tuple then some @@ -4578,7 +4680,7 @@ l3: * don't check for this in the multixact case, because some * locker transactions might still be running. */ - UpdateXmaxHintBits(tuple->t_data, *buffer, xwait); + UpdateXmaxHintBits(tuple->t_data, buffer, xwait); } } @@ -4637,9 +4739,9 @@ failed: */ if (vmbuffer == InvalidBuffer && PageIsAllVisible(page)) { - LockBuffer(*buffer, BUFFER_LOCK_UNLOCK); + LockBuffer(buffer, BUFFER_LOCK_UNLOCK); visibilitymap_pin(relation, block, &vmbuffer); - LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); goto l3; } @@ -4702,7 +4804,7 @@ failed: cleared_all_frozen = true; - MarkBufferDirty(*buffer); + MarkBufferDirty(buffer); /* * XLOG stuff. You might think that we don't need an XLOG record because @@ -4722,7 +4824,7 @@ failed: XLogRecPtr recptr; XLogBeginInsert(); - XLogRegisterBuffer(0, *buffer, REGBUF_STANDARD); + XLogRegisterBuffer(0, buffer, REGBUF_STANDARD); xlrec.offnum = ItemPointerGetOffsetNumber(&tuple->t_self); xlrec.locking_xid = xid; @@ -4743,7 +4845,7 @@ failed: result = TM_Ok; out_locked: - LockBuffer(*buffer, BUFFER_LOCK_UNLOCK); + LockBuffer(buffer, BUFFER_LOCK_UNLOCK); out_unlocked: if (BufferIsValid(vmbuffer)) @@ -4761,6 +4863,9 @@ out_unlocked: if (have_tuple_lock) UnlockTupleTuplock(relation, tid, mode); + /* Put the target tuple to the slot */ + ExecStorePinnedBufferHeapTuple(tuple, slot, buffer); + return result; } diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 97b5daee920..5781096203d 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -45,11 +45,11 @@ #include "utils/builtins.h" #include "utils/rel.h" -static TM_Result heapam_tuple_lock_internal(Relation relation, ItemPointer tid, - Snapshot snapshot, TupleTableSlot *slot, - CommandId cid, LockTupleMode mode, - LockWaitPolicy wait_policy, uint8 flags, - TM_FailureData *tmfd, bool updated); +static TM_Result heapam_tuple_lock(Relation relation, ItemPointer tid, + Snapshot snapshot, TupleTableSlot *slot, + CommandId cid, LockTupleMode mode, + LockWaitPolicy wait_policy, uint8 flags, + TM_FailureData *tmfd); static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, @@ -304,9 +304,9 @@ heapam_tuple_complete_speculative(Relation relation, TupleTableSlot *slot, static TM_Result heapam_tuple_delete(Relation relation, ItemPointer tid, CommandId cid, - Snapshot snapshot, Snapshot crosscheck, bool wait, + Snapshot snapshot, Snapshot crosscheck, int options, TM_FailureData *tmfd, bool changingPart, - LazyTupleTableSlot *lockedSlot) + TupleTableSlot *oldSlot) { TM_Result result; @@ -315,33 +315,32 @@ heapam_tuple_delete(Relation relation, ItemPointer tid, CommandId cid, * the storage itself is cleaning the dead tuples by itself, it is the * time to call the index tuple deletion also. */ - result = heap_delete(relation, tid, cid, crosscheck, wait, - tmfd, changingPart); + result = heap_delete(relation, tid, cid, crosscheck, options, + tmfd, changingPart, oldSlot); /* * If the tuple has been concurrently updated, then get the lock on it. - * (Do this if caller asked for tat by providing a 'lockedSlot'.) With the - * lock held retry of delete should succeed even if there are more - * concurrent update attempts. + * (Do only if caller asked for this by setting the + * TABLE_MODIFY_LOCK_UPDATED option) With the lock held retry of the + * delete should succeed even if there are more concurrent update + * attempts. */ - if (result == TM_Updated && lockedSlot) + if (result == TM_Updated && (options & TABLE_MODIFY_LOCK_UPDATED)) { - TupleTableSlot *evalSlot; - - Assert(wait); - - evalSlot = LAZY_TTS_EVAL(lockedSlot); - result = heapam_tuple_lock_internal(relation, tid, snapshot, - evalSlot, cid, LockTupleExclusive, - LockWaitBlock, - TUPLE_LOCK_FLAG_FIND_LAST_VERSION, - tmfd, true); + /* + * heapam_tuple_lock() will take advantage of tuple loaded into + * oldSlot by heap_delete(). + */ + result = heapam_tuple_lock(relation, tid, snapshot, + oldSlot, cid, LockTupleExclusive, + (options & TABLE_MODIFY_WAIT) ? + LockWaitBlock : + LockWaitSkip, + TUPLE_LOCK_FLAG_FIND_LAST_VERSION, + tmfd); if (result == TM_Ok) - { - tmfd->traversed = true; return TM_Updated; - } } return result; @@ -351,9 +350,9 @@ heapam_tuple_delete(Relation relation, ItemPointer tid, CommandId cid, static TM_Result heapam_tuple_update(Relation relation, ItemPointer otid, TupleTableSlot *slot, CommandId cid, Snapshot snapshot, Snapshot crosscheck, - bool wait, TM_FailureData *tmfd, + int options, TM_FailureData *tmfd, LockTupleMode *lockmode, TU_UpdateIndexes *update_indexes, - LazyTupleTableSlot *lockedSlot) + TupleTableSlot *oldSlot) { bool shouldFree = true; HeapTuple tuple = ExecFetchSlotHeapTuple(slot, true, &shouldFree); @@ -363,8 +362,8 @@ heapam_tuple_update(Relation relation, ItemPointer otid, TupleTableSlot *slot, slot->tts_tableOid = RelationGetRelid(relation); tuple->t_tableOid = slot->tts_tableOid; - result = heap_update(relation, otid, tuple, cid, crosscheck, wait, - tmfd, lockmode, update_indexes); + result = heap_update(relation, otid, tuple, cid, crosscheck, options, + tmfd, lockmode, update_indexes, oldSlot); ItemPointerCopy(&tuple->t_self, &slot->tts_tid); /* @@ -373,8 +372,8 @@ heapam_tuple_update(Relation relation, ItemPointer otid, TupleTableSlot *slot, * Note: heap_update returns the tid (location) of the new tuple in the * t_self field. * - * If the update is not HOT, we must update all indexes. If the update - * is HOT, it could be that we updated summarized columns, so we either + * If the update is not HOT, we must update all indexes. If the update is + * HOT, it could be that we updated summarized columns, so we either * update only summarized indexes, or none at all. */ if (result != TM_Ok) @@ -393,28 +392,27 @@ heapam_tuple_update(Relation relation, ItemPointer otid, TupleTableSlot *slot, /* * If the tuple has been concurrently updated, then get the lock on it. - * (Do this if caller asked for tat by providing a 'lockedSlot'.) With the - * lock held retry of update should succeed even if there are more - * concurrent update attempts. + * (Do only if caller asked for this by setting the + * TABLE_MODIFY_LOCK_UPDATED option) With the lock held retry of the + * update should succeed even if there are more concurrent update + * attempts. */ - if (result == TM_Updated && lockedSlot) + if (result == TM_Updated && (options & TABLE_MODIFY_LOCK_UPDATED)) { - TupleTableSlot *evalSlot; - - Assert(wait); - - evalSlot = LAZY_TTS_EVAL(lockedSlot); - result = heapam_tuple_lock_internal(relation, otid, snapshot, - evalSlot, cid, *lockmode, - LockWaitBlock, - TUPLE_LOCK_FLAG_FIND_LAST_VERSION, - tmfd, true); + /* + * heapam_tuple_lock() will take advantage of tuple loaded into + * oldSlot by heap_update(). + */ + result = heapam_tuple_lock(relation, otid, snapshot, + oldSlot, cid, *lockmode, + (options & TABLE_MODIFY_WAIT) ? + LockWaitBlock : + LockWaitSkip, + TUPLE_LOCK_FLAG_FIND_LAST_VERSION, + tmfd); if (result == TM_Ok) - { - tmfd->traversed = true; return TM_Updated; - } } return result; @@ -425,26 +423,9 @@ heapam_tuple_lock(Relation relation, ItemPointer tid, Snapshot snapshot, TupleTableSlot *slot, CommandId cid, LockTupleMode mode, LockWaitPolicy wait_policy, uint8 flags, TM_FailureData *tmfd) -{ - return heapam_tuple_lock_internal(relation, tid, snapshot, slot, cid, - mode, wait_policy, flags, tmfd, false); -} - -/* - * This routine does the work for heapam_tuple_lock(), but also support - * `updated` argument to re-use the work done by heapam_tuple_update() or - * heapam_tuple_delete() on figuring out that tuple was concurrently updated. - */ -static TM_Result -heapam_tuple_lock_internal(Relation relation, ItemPointer tid, - Snapshot snapshot, TupleTableSlot *slot, - CommandId cid, LockTupleMode mode, - LockWaitPolicy wait_policy, uint8 flags, - TM_FailureData *tmfd, bool updated) { BufferHeapTupleTableSlot *bslot = (BufferHeapTupleTableSlot *) slot; TM_Result result; - Buffer buffer = InvalidBuffer; HeapTuple tuple = &bslot->base.tupdata; bool follow_updates; @@ -454,27 +435,14 @@ heapam_tuple_lock_internal(Relation relation, ItemPointer tid, Assert(TTS_IS_BUFFERTUPLE(slot)); tuple_lock_retry: - tuple->t_self = *tid; - if (!updated) - result = heap_lock_tuple(relation, tuple, cid, mode, wait_policy, - follow_updates, &buffer, tmfd); - else - result = TM_Updated; + result = heap_lock_tuple(relation, tid, slot, cid, mode, wait_policy, + follow_updates, tmfd); if (result == TM_Updated && (flags & TUPLE_LOCK_FLAG_FIND_LAST_VERSION)) { - if (!updated) - { - /* Should not encounter speculative tuple on recheck */ - Assert(!HeapTupleHeaderIsSpeculative(tuple->t_data)); - - ReleaseBuffer(buffer); - } - else - { - updated = false; - } + /* Should not encounter speculative tuple on recheck */ + Assert(!HeapTupleHeaderIsSpeculative(tuple->t_data)); if (!ItemPointerEquals(&tmfd->ctid, &tuple->t_self)) { @@ -497,6 +465,8 @@ tuple_lock_retry: InitDirtySnapshot(SnapshotDirty); for (;;) { + Buffer buffer = InvalidBuffer; + if (ItemPointerIndicatesMovedPartitions(tid)) ereport(ERROR, (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE), @@ -591,7 +561,7 @@ tuple_lock_retry: /* * This is a live tuple, so try to lock it again. */ - ReleaseBuffer(buffer); + ExecStorePinnedBufferHeapTuple(tuple, slot, buffer); goto tuple_lock_retry; } @@ -602,7 +572,7 @@ tuple_lock_retry: */ if (tuple->t_data == NULL) { - Assert(!BufferIsValid(buffer)); + ReleaseBuffer(buffer); return TM_Deleted; } @@ -655,9 +625,6 @@ tuple_lock_retry: slot->tts_tableOid = RelationGetRelid(relation); tuple->t_tableOid = slot->tts_tableOid; - /* store in slot, transferring existing pin */ - ExecStorePinnedBufferHeapTuple(tuple, slot, buffer); - return result; } diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c index 2a1a6ced3c7..0167a2fb1fc 100644 --- a/src/backend/access/table/tableam.c +++ b/src/backend/access/table/tableam.c @@ -297,17 +297,23 @@ simple_table_tuple_insert(Relation rel, TupleTableSlot *slot) * via ereport(). */ void -simple_table_tuple_delete(Relation rel, ItemPointer tid, Snapshot snapshot) +simple_table_tuple_delete(Relation rel, ItemPointer tid, Snapshot snapshot, + TupleTableSlot *oldSlot) { TM_Result result; TM_FailureData tmfd; + int options = TABLE_MODIFY_WAIT; /* wait for commit */ + + /* Fetch old tuple if the relevant slot is provided */ + if (oldSlot) + options |= TABLE_MODIFY_FETCH_OLD_TUPLE; result = table_tuple_delete(rel, tid, GetCurrentCommandId(true), snapshot, InvalidSnapshot, - true /* wait for commit */ , + options, &tmfd, false /* changingPart */ , - NULL); + oldSlot); switch (result) { @@ -346,18 +352,24 @@ void simple_table_tuple_update(Relation rel, ItemPointer otid, TupleTableSlot *slot, Snapshot snapshot, - TU_UpdateIndexes *update_indexes) + TU_UpdateIndexes *update_indexes, + TupleTableSlot *oldSlot) { TM_Result result; TM_FailureData tmfd; LockTupleMode lockmode; + int options = TABLE_MODIFY_WAIT; /* wait for commit */ + + /* Fetch old tuple if the relevant slot is provided */ + if (oldSlot) + options |= TABLE_MODIFY_FETCH_OLD_TUPLE; result = table_tuple_update(rel, otid, slot, GetCurrentCommandId(true), snapshot, InvalidSnapshot, - true /* wait for commit */ , + options, &tmfd, &lockmode, update_indexes, - NULL); + oldSlot); switch (result) { diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c index 0f2de7e2e01..5c4f8bae188 100644 --- a/src/backend/commands/trigger.c +++ b/src/backend/commands/trigger.c @@ -2784,8 +2784,8 @@ ExecBRDeleteTriggers(EState *estate, EPQState *epqstate, void ExecARDeleteTriggers(EState *estate, ResultRelInfo *relinfo, - ItemPointer tupleid, HeapTuple fdw_trigtuple, + TupleTableSlot *slot, TransitionCaptureState *transition_capture, bool is_crosspart_update) { @@ -2794,20 +2794,11 @@ ExecARDeleteTriggers(EState *estate, if ((trigdesc && trigdesc->trig_delete_after_row) || (transition_capture && transition_capture->tcs_delete_old_table)) { - TupleTableSlot *slot = ExecGetTriggerOldSlot(estate, relinfo); - - Assert(HeapTupleIsValid(fdw_trigtuple) ^ ItemPointerIsValid(tupleid)); - if (fdw_trigtuple == NULL) - GetTupleForTrigger(estate, - NULL, - relinfo, - tupleid, - LockTupleExclusive, - slot, - NULL, - NULL, - NULL); - else + /* + * Put the FDW old tuple to the slot. Otherwise, caller is expected + * to have old tuple alredy fetched to the slot. + */ + if (fdw_trigtuple != NULL) ExecForceStoreHeapTuple(fdw_trigtuple, slot, false); AfterTriggerSaveEvent(estate, relinfo, NULL, NULL, @@ -3080,18 +3071,17 @@ ExecBRUpdateTriggers(EState *estate, EPQState *epqstate, * Note: 'src_partinfo' and 'dst_partinfo', when non-NULL, refer to the source * and destination partitions, respectively, of a cross-partition update of * the root partitioned table mentioned in the query, given by 'relinfo'. - * 'tupleid' in that case refers to the ctid of the "old" tuple in the source - * partition, and 'newslot' contains the "new" tuple in the destination - * partition. This interface allows to support the requirements of - * ExecCrossPartitionUpdateForeignKey(); is_crosspart_update must be true in - * that case. + * 'oldslot' contains the "old" tuple in the source partition, and 'newslot' + * contains the "new" tuple in the destination partition. This interface + * allows to support the requirements of ExecCrossPartitionUpdateForeignKey(); + * is_crosspart_update must be true in that case. */ void ExecARUpdateTriggers(EState *estate, ResultRelInfo *relinfo, ResultRelInfo *src_partinfo, ResultRelInfo *dst_partinfo, - ItemPointer tupleid, HeapTuple fdw_trigtuple, + TupleTableSlot *oldslot, TupleTableSlot *newslot, List *recheckIndexes, TransitionCaptureState *transition_capture, @@ -3110,29 +3100,14 @@ ExecARUpdateTriggers(EState *estate, ResultRelInfo *relinfo, * separately for DELETE and INSERT to capture transition table rows. * In such case, either old tuple or new tuple can be NULL. */ - TupleTableSlot *oldslot; - ResultRelInfo *tupsrc; - Assert((src_partinfo != NULL && dst_partinfo != NULL) || !is_crosspart_update); - tupsrc = src_partinfo ? src_partinfo : relinfo; - oldslot = ExecGetTriggerOldSlot(estate, tupsrc); - - if (fdw_trigtuple == NULL && ItemPointerIsValid(tupleid)) - GetTupleForTrigger(estate, - NULL, - tupsrc, - tupleid, - LockTupleExclusive, - oldslot, - NULL, - NULL, - NULL); - else if (fdw_trigtuple != NULL) + if (fdw_trigtuple != NULL) + { + Assert(oldslot); ExecForceStoreHeapTuple(fdw_trigtuple, oldslot, false); - else - ExecClearTuple(oldslot); + } AfterTriggerSaveEvent(estate, relinfo, src_partinfo, dst_partinfo, diff --git a/src/backend/executor/execReplication.c b/src/backend/executor/execReplication.c index 9dd71684615..31ff5cd9f41 100644 --- a/src/backend/executor/execReplication.c +++ b/src/backend/executor/execReplication.c @@ -545,6 +545,7 @@ ExecSimpleRelationUpdate(ResultRelInfo *resultRelInfo, { List *recheckIndexes = NIL; TU_UpdateIndexes update_indexes; + TupleTableSlot *oldSlot = NULL; /* Compute stored generated columns */ if (rel->rd_att->constr && @@ -558,8 +559,12 @@ ExecSimpleRelationUpdate(ResultRelInfo *resultRelInfo, if (rel->rd_rel->relispartition) ExecPartitionCheck(resultRelInfo, slot, estate, true); + if (resultRelInfo->ri_TrigDesc && + resultRelInfo->ri_TrigDesc->trig_update_after_row) + oldSlot = ExecGetTriggerOldSlot(estate, resultRelInfo); + simple_table_tuple_update(rel, tid, slot, estate->es_snapshot, - &update_indexes); + &update_indexes, oldSlot); if (resultRelInfo->ri_NumIndices > 0 && (update_indexes != TU_None)) recheckIndexes = ExecInsertIndexTuples(resultRelInfo, @@ -570,7 +575,7 @@ ExecSimpleRelationUpdate(ResultRelInfo *resultRelInfo, /* AFTER ROW UPDATE Triggers */ ExecARUpdateTriggers(estate, resultRelInfo, NULL, NULL, - tid, NULL, slot, + NULL, oldSlot, slot, recheckIndexes, NULL, false); list_free(recheckIndexes); @@ -604,12 +609,18 @@ ExecSimpleRelationDelete(ResultRelInfo *resultRelInfo, if (!skip_tuple) { + TupleTableSlot *oldSlot = NULL; + + if (resultRelInfo->ri_TrigDesc && + resultRelInfo->ri_TrigDesc->trig_delete_after_row) + oldSlot = ExecGetTriggerOldSlot(estate, resultRelInfo); + /* OK, delete the tuple */ - simple_table_tuple_delete(rel, tid, estate->es_snapshot); + simple_table_tuple_delete(rel, tid, estate->es_snapshot, oldSlot); /* AFTER ROW DELETE Triggers */ ExecARDeleteTriggers(estate, resultRelInfo, - tid, NULL, NULL, false); + NULL, oldSlot, NULL, false); } } diff --git a/src/backend/executor/nodeModifyTable.c b/src/backend/executor/nodeModifyTable.c index e3503756818..de49e48bae6 100644 --- a/src/backend/executor/nodeModifyTable.c +++ b/src/backend/executor/nodeModifyTable.c @@ -111,7 +111,7 @@ typedef struct UpdateContext { bool updated; /* did UPDATE actually occur? */ bool crossPartUpdate; /* was it a cross-partition update? */ - TU_UpdateIndexes updateIndexes; /* Which index updates are required? */ + TU_UpdateIndexes updateIndexes; /* Which index updates are required? */ /* * Lock mode to acquire on the latest tuple version before performing @@ -133,7 +133,7 @@ static void ExecCrossPartitionUpdateForeignKey(ModifyTableContext *context, ResultRelInfo *sourcePartInfo, ResultRelInfo *destPartInfo, ItemPointer tupleid, - TupleTableSlot *oldslot, + TupleTableSlot *oldSlot, TupleTableSlot *newslot); static bool ExecOnConflictUpdate(ModifyTableContext *context, ResultRelInfo *resultRelInfo, @@ -570,6 +570,10 @@ ExecInitInsertProjection(ModifyTableState *mtstate, resultRelInfo->ri_newTupleSlot = table_slot_create(resultRelInfo->ri_RelationDesc, &estate->es_tupleTable); + if (node->onConflictAction == ONCONFLICT_UPDATE) + resultRelInfo->ri_oldTupleSlot = + table_slot_create(resultRelInfo->ri_RelationDesc, + &estate->es_tupleTable); /* Build ProjectionInfo if needed (it probably isn't). */ if (need_projection) @@ -1160,7 +1164,7 @@ ExecInsert(ModifyTableContext *context, ExecARUpdateTriggers(estate, resultRelInfo, NULL, NULL, NULL, - NULL, + resultRelInfo->ri_oldTupleSlot, slot, NULL, mtstate->mt_transition_capture, @@ -1324,62 +1328,28 @@ ExecDeletePrologue(ModifyTableContext *context, ResultRelInfo *resultRelInfo, return true; } -/* - * The implementation for LazyTupleTableSlot wrapper for EPQ slot to be passed - * to table_tuple_update()/table_tuple_delete(). - */ -typedef struct -{ - EPQState *epqstate; - ResultRelInfo *resultRelInfo; -} GetEPQSlotArg; - -static TupleTableSlot * -GetEPQSlot(void *arg) -{ - GetEPQSlotArg *slotArg = (GetEPQSlotArg *) arg; - - return EvalPlanQualSlot(slotArg->epqstate, - slotArg->resultRelInfo->ri_RelationDesc, - slotArg->resultRelInfo->ri_RangeTableIndex); -} - /* * ExecDeleteAct -- subroutine for ExecDelete * * Actually delete the tuple from a plain table. * - * If the 'lockUpdated' flag is set and the target tuple is updated, then - * the latest version gets locked and fetched into the EPQ slot. - * * Caller is in charge of doing EvalPlanQual as necessary */ static TM_Result ExecDeleteAct(ModifyTableContext *context, ResultRelInfo *resultRelInfo, - ItemPointer tupleid, bool changingPart, bool lockUpdated) + ItemPointer tupleid, bool changingPart, int options, + TupleTableSlot *oldSlot) { EState *estate = context->estate; - GetEPQSlotArg slotArg = {context->epqstate, resultRelInfo}; - LazyTupleTableSlot lazyEPQSlot, - *lazyEPQSlotPtr; - if (lockUpdated) - { - MAKE_LAZY_TTS(&lazyEPQSlot, GetEPQSlot, &slotArg); - lazyEPQSlotPtr = &lazyEPQSlot; - } - else - { - lazyEPQSlotPtr = NULL; - } return table_tuple_delete(resultRelInfo->ri_RelationDesc, tupleid, estate->es_output_cid, estate->es_snapshot, estate->es_crosscheck_snapshot, - true /* wait for commit */ , + options /* wait for commit */ , &context->tmfd, changingPart, - lazyEPQSlotPtr); + oldSlot); } /* @@ -1391,7 +1361,8 @@ ExecDeleteAct(ModifyTableContext *context, ResultRelInfo *resultRelInfo, */ static void ExecDeleteEpilogue(ModifyTableContext *context, ResultRelInfo *resultRelInfo, - ItemPointer tupleid, HeapTuple oldtuple, bool changingPart) + ItemPointer tupleid, HeapTuple oldtuple, + TupleTableSlot *slot, bool changingPart) { ModifyTableState *mtstate = context->mtstate; EState *estate = context->estate; @@ -1409,8 +1380,8 @@ ExecDeleteEpilogue(ModifyTableContext *context, ResultRelInfo *resultRelInfo, { ExecARUpdateTriggers(estate, resultRelInfo, NULL, NULL, - tupleid, oldtuple, - NULL, NULL, mtstate->mt_transition_capture, + oldtuple, + slot, NULL, NULL, mtstate->mt_transition_capture, false); /* @@ -1421,10 +1392,30 @@ ExecDeleteEpilogue(ModifyTableContext *context, ResultRelInfo *resultRelInfo, } /* AFTER ROW DELETE Triggers */ - ExecARDeleteTriggers(estate, resultRelInfo, tupleid, oldtuple, + ExecARDeleteTriggers(estate, resultRelInfo, oldtuple, slot, ar_delete_trig_tcs, changingPart); } +/* + * Initializes the tuple slot in a ResultRelInfo for DELETE action. + * + * We mark 'projectNewInfoValid' even though the projections themselves + * are not initialized here. + */ +static void +ExecInitDeleteTupleSlot(ModifyTableState *mtstate, + ResultRelInfo *resultRelInfo) +{ + EState *estate = mtstate->ps.state; + + Assert(!resultRelInfo->ri_projectNewInfoValid); + + resultRelInfo->ri_oldTupleSlot = + table_slot_create(resultRelInfo->ri_RelationDesc, + &estate->es_tupleTable); + resultRelInfo->ri_projectNewInfoValid = true; +} + /* ---------------------------------------------------------------- * ExecDelete * @@ -1452,6 +1443,7 @@ ExecDelete(ModifyTableContext *context, ResultRelInfo *resultRelInfo, ItemPointer tupleid, HeapTuple oldtuple, + TupleTableSlot *oldSlot, bool processReturning, bool changingPart, bool canSetTag, @@ -1514,6 +1506,11 @@ ExecDelete(ModifyTableContext *context, } else { + int options = TABLE_MODIFY_WAIT | TABLE_MODIFY_FETCH_OLD_TUPLE; + + if (!IsolationUsesXactSnapshot()) + options |= TABLE_MODIFY_LOCK_UPDATED; + /* * delete the tuple * @@ -1525,7 +1522,7 @@ ExecDelete(ModifyTableContext *context, */ ldelete: result = ExecDeleteAct(context, resultRelInfo, tupleid, changingPart, - !IsolationUsesXactSnapshot()); + options, oldSlot); switch (result) { @@ -1569,7 +1566,6 @@ ldelete: case TM_Updated: { - TupleTableSlot *inputslot; TupleTableSlot *epqslot; if (IsolationUsesXactSnapshot()) @@ -1578,34 +1574,14 @@ ldelete: errmsg("could not serialize access due to concurrent update"))); /* - * ExecDeleteAct() has already locked the old tuple for - * us. Now we need to copy it to the right slot. - */ - EvalPlanQualBegin(context->epqstate); - inputslot = EvalPlanQualSlot(context->epqstate, resultRelationDesc, - resultRelInfo->ri_RangeTableIndex); - - /* - * Save locked table for further processing for RETURNING - * clause. + * We need to do EPQ. The latest tuple is already found + * and locked as a result of TABLE_MODIFY_LOCK_UPDATED. */ - if (processReturning && - resultRelInfo->ri_projectReturning && - !resultRelInfo->ri_FdwRoutine) - { - TupleTableSlot *returningSlot; - - returningSlot = ExecGetReturningSlot(estate, - resultRelInfo); - ExecCopySlot(returningSlot, inputslot); - ExecMaterializeSlot(returningSlot); - } - Assert(context->tmfd.traversed); epqslot = EvalPlanQual(context->epqstate, resultRelationDesc, resultRelInfo->ri_RangeTableIndex, - inputslot); + oldSlot); if (TupIsNull(epqslot)) /* Tuple not passing quals anymore, exiting... */ return NULL; @@ -1654,7 +1630,8 @@ ldelete: if (tupleDeleted) *tupleDeleted = true; - ExecDeleteEpilogue(context, resultRelInfo, tupleid, oldtuple, changingPart); + ExecDeleteEpilogue(context, resultRelInfo, tupleid, oldtuple, + oldSlot, changingPart); /* Process RETURNING if present and if requested */ if (processReturning && resultRelInfo->ri_projectReturning) @@ -1672,22 +1649,13 @@ ldelete: } else { - /* - * Tuple can be already fetched to the returning slot in case - * we've previously locked it. Fetch the tuple only if the slot - * is empty. - */ + /* Copy old tuple to the returning slot */ slot = ExecGetReturningSlot(estate, resultRelInfo); if (oldtuple != NULL) - { ExecForceStoreHeapTuple(oldtuple, slot, false); - } - else if (TupIsNull(slot)) - { - if (!table_tuple_fetch_row_version(resultRelationDesc, tupleid, - SnapshotAny, slot)) - elog(ERROR, "failed to fetch deleted tuple for DELETE RETURNING"); - } + else + ExecCopySlot(slot, oldSlot); + Assert(!TupIsNull(slot)); } rslot = ExecProcessReturning(resultRelInfo, slot, context->planSlot); @@ -1786,12 +1754,16 @@ ExecCrossPartitionUpdate(ModifyTableContext *context, MemoryContextSwitchTo(oldcxt); } + /* Make sure ri_oldTupleSlot is initialized. */ + if (unlikely(!resultRelInfo->ri_projectNewInfoValid)) + ExecInitUpdateProjection(mtstate, resultRelInfo); + /* * Row movement, part 1. Delete the tuple, but skip RETURNING processing. * We want to return rows from INSERT. */ ExecDelete(context, resultRelInfo, - tupleid, oldtuple, + tupleid, oldtuple, resultRelInfo->ri_oldTupleSlot, false, /* processReturning */ true, /* changingPart */ false, /* canSetTag */ @@ -1832,21 +1804,13 @@ ExecCrossPartitionUpdate(ModifyTableContext *context, return true; else { - /* Fetch the most recent version of old tuple. */ - TupleTableSlot *oldSlot; - - /* ... but first, make sure ri_oldTupleSlot is initialized. */ - if (unlikely(!resultRelInfo->ri_projectNewInfoValid)) - ExecInitUpdateProjection(mtstate, resultRelInfo); - oldSlot = resultRelInfo->ri_oldTupleSlot; - if (!table_tuple_fetch_row_version(resultRelInfo->ri_RelationDesc, - tupleid, - SnapshotAny, - oldSlot)) - elog(ERROR, "failed to fetch tuple being updated"); - /* and project the new tuple to retry the UPDATE with */ + /* + * ExecDelete already fetches the most recent version of old tuple + * to resultRelInfo->ri_RelationDesc. So, just project the new + * tuple to retry the UPDATE with. + */ *retry_slot = ExecGetUpdateNewTuple(resultRelInfo, epqslot, - oldSlot); + resultRelInfo->ri_oldTupleSlot); return false; } } @@ -1965,15 +1929,13 @@ ExecUpdatePrepareSlot(ResultRelInfo *resultRelInfo, static TM_Result ExecUpdateAct(ModifyTableContext *context, ResultRelInfo *resultRelInfo, ItemPointer tupleid, HeapTuple oldtuple, TupleTableSlot *slot, - bool canSetTag, bool lockUpdated, UpdateContext *updateCxt) + bool canSetTag, int options, TupleTableSlot *oldSlot, + UpdateContext *updateCxt) { EState *estate = context->estate; Relation resultRelationDesc = resultRelInfo->ri_RelationDesc; bool partition_constraint_failed; TM_Result result; - GetEPQSlotArg slotArg = {context->epqstate, resultRelInfo}; - LazyTupleTableSlot lazyEPQSlot, - *lazyEPQSlotPtr; updateCxt->crossPartUpdate = false; @@ -2060,7 +2022,8 @@ lreplace: ExecCrossPartitionUpdateForeignKey(context, resultRelInfo, insert_destrel, - tupleid, slot, + tupleid, + resultRelInfo->ri_oldTupleSlot, inserted_tuple); return TM_Ok; @@ -2099,23 +2062,14 @@ lreplace: * for referential integrity updates in transaction-snapshot mode * transactions. */ - if (lockUpdated) - { - MAKE_LAZY_TTS(&lazyEPQSlot, GetEPQSlot, &slotArg); - lazyEPQSlotPtr = &lazyEPQSlot; - } - else - { - lazyEPQSlotPtr = NULL; - } result = table_tuple_update(resultRelationDesc, tupleid, slot, estate->es_output_cid, estate->es_snapshot, estate->es_crosscheck_snapshot, - true /* wait for commit */ , + options /* wait for commit */ , &context->tmfd, &updateCxt->lockmode, &updateCxt->updateIndexes, - lazyEPQSlotPtr); + oldSlot); if (result == TM_Ok) updateCxt->updated = true; @@ -2131,7 +2085,8 @@ lreplace: static void ExecUpdateEpilogue(ModifyTableContext *context, UpdateContext *updateCxt, ResultRelInfo *resultRelInfo, ItemPointer tupleid, - HeapTuple oldtuple, TupleTableSlot *slot) + HeapTuple oldtuple, TupleTableSlot *slot, + TupleTableSlot *oldSlot) { ModifyTableState *mtstate = context->mtstate; List *recheckIndexes = NIL; @@ -2147,7 +2102,7 @@ ExecUpdateEpilogue(ModifyTableContext *context, UpdateContext *updateCxt, /* AFTER ROW UPDATE Triggers */ ExecARUpdateTriggers(context->estate, resultRelInfo, NULL, NULL, - tupleid, oldtuple, slot, + oldtuple, oldSlot, slot, recheckIndexes, mtstate->operation == CMD_INSERT ? mtstate->mt_oc_transition_capture : @@ -2236,7 +2191,7 @@ ExecCrossPartitionUpdateForeignKey(ModifyTableContext *context, /* Perform the root table's triggers. */ ExecARUpdateTriggers(context->estate, rootRelInfo, sourcePartInfo, destPartInfo, - tupleid, NULL, newslot, NIL, NULL, true); + NULL, oldslot, newslot, NIL, NULL, true); } /* ---------------------------------------------------------------- @@ -2259,6 +2214,7 @@ ExecCrossPartitionUpdateForeignKey(ModifyTableContext *context, * no relevant triggers. * * slot contains the new tuple value to be stored. + * oldSlot is the slot to store the old tuple. * planSlot is the output of the ModifyTable's subplan; we use it * to access values from other input tables (for RETURNING), * row-ID junk columns, etc. @@ -2269,7 +2225,7 @@ ExecCrossPartitionUpdateForeignKey(ModifyTableContext *context, static TupleTableSlot * ExecUpdate(ModifyTableContext *context, ResultRelInfo *resultRelInfo, ItemPointer tupleid, HeapTuple oldtuple, TupleTableSlot *slot, - bool canSetTag, bool locked) + TupleTableSlot *oldSlot, bool canSetTag, bool locked) { EState *estate = context->estate; Relation resultRelationDesc = resultRelInfo->ri_RelationDesc; @@ -2322,6 +2278,11 @@ ExecUpdate(ModifyTableContext *context, ResultRelInfo *resultRelInfo, } else { + int options = TABLE_MODIFY_WAIT | TABLE_MODIFY_FETCH_OLD_TUPLE; + + if (!locked && !IsolationUsesXactSnapshot()) + options |= TABLE_MODIFY_LOCK_UPDATED; + /* * If we generate a new candidate tuple after EvalPlanQual testing, we * must loop back here to try again. (We don't need to redo triggers, @@ -2331,8 +2292,7 @@ ExecUpdate(ModifyTableContext *context, ResultRelInfo *resultRelInfo, */ redo_act: result = ExecUpdateAct(context, resultRelInfo, tupleid, oldtuple, slot, - canSetTag, !IsolationUsesXactSnapshot(), - &updateCxt); + canSetTag, options, oldSlot, &updateCxt); /* * If ExecUpdateAct reports that a cross-partition update was done, @@ -2383,9 +2343,7 @@ redo_act: case TM_Updated: { - TupleTableSlot *inputslot; TupleTableSlot *epqslot; - TupleTableSlot *oldSlot; if (IsolationUsesXactSnapshot()) ereport(ERROR, @@ -2394,35 +2352,20 @@ redo_act: Assert(!locked); /* - * ExecUpdateAct() has already locked the old tuple for - * us. Now we need to copy it to the right slot. + * We need to do EPQ. The latest tuple is already found + * and locked as a result of TABLE_MODIFY_LOCK_UPDATED. */ - inputslot = EvalPlanQualSlot(context->epqstate, resultRelationDesc, - resultRelInfo->ri_RangeTableIndex); - - /* Make sure ri_oldTupleSlot is initialized. */ - if (unlikely(!resultRelInfo->ri_projectNewInfoValid)) - ExecInitUpdateProjection(context->mtstate, - resultRelInfo); - - /* - * Save the locked tuple for further calculation of the - * new tuple. - */ - oldSlot = resultRelInfo->ri_oldTupleSlot; - ExecCopySlot(oldSlot, inputslot); - ExecMaterializeSlot(oldSlot); Assert(context->tmfd.traversed); - epqslot = EvalPlanQual(context->epqstate, resultRelationDesc, resultRelInfo->ri_RangeTableIndex, - inputslot); + oldSlot); if (TupIsNull(epqslot)) /* Tuple not passing quals anymore, exiting... */ return NULL; slot = ExecGetUpdateNewTuple(resultRelInfo, - epqslot, oldSlot); + epqslot, + oldSlot); goto redo_act; } @@ -2447,7 +2390,7 @@ redo_act: (estate->es_processed)++; ExecUpdateEpilogue(context, &updateCxt, resultRelInfo, tupleid, oldtuple, - slot); + slot, oldSlot); /* Process RETURNING if present */ if (resultRelInfo->ri_projectReturning) @@ -2665,6 +2608,7 @@ ExecOnConflictUpdate(ModifyTableContext *context, *returning = ExecUpdate(context, resultRelInfo, conflictTid, NULL, resultRelInfo->ri_onConflict->oc_ProjSlot, + existing, canSetTag, true); /* @@ -2803,7 +2747,6 @@ lmerge_matched: * EvalPlanQual returns us a new tuple, which may not be visible to our * MVCC snapshot. */ - if (!table_tuple_fetch_row_version(resultRelInfo->ri_RelationDesc, tupleid, SnapshotAny, @@ -2868,11 +2811,13 @@ lmerge_matched: break; /* concurrent update/delete */ } result = ExecUpdateAct(context, resultRelInfo, tupleid, NULL, - newslot, false, false, &updateCxt); + newslot, false, TABLE_MODIFY_WAIT, NULL, + &updateCxt); if (result == TM_Ok && updateCxt.updated) { ExecUpdateEpilogue(context, &updateCxt, resultRelInfo, - tupleid, NULL, newslot); + tupleid, NULL, newslot, + resultRelInfo->ri_oldTupleSlot); mtstate->mt_merge_updated += 1; } break; @@ -2887,11 +2832,11 @@ lmerge_matched: break; /* concurrent update/delete */ } result = ExecDeleteAct(context, resultRelInfo, tupleid, - false, false); + false, TABLE_MODIFY_WAIT, NULL); if (result == TM_Ok) { ExecDeleteEpilogue(context, resultRelInfo, tupleid, NULL, - false); + resultRelInfo->ri_oldTupleSlot, false); mtstate->mt_merge_deleted += 1; } break; @@ -3793,12 +3738,18 @@ ExecModifyTable(PlanState *pstate) /* Now apply the update. */ slot = ExecUpdate(&context, resultRelInfo, tupleid, oldtuple, - slot, node->canSetTag, false); + slot, resultRelInfo->ri_oldTupleSlot, + node->canSetTag, false); break; case CMD_DELETE: + /* Initialize slot for DELETE to fetch the old tuple */ + if (unlikely(!resultRelInfo->ri_projectNewInfoValid)) + ExecInitDeleteTupleSlot(node, resultRelInfo); + slot = ExecDelete(&context, resultRelInfo, tupleid, oldtuple, - true, false, node->canSetTag, NULL, NULL); + resultRelInfo->ri_oldTupleSlot, true, false, + node->canSetTag, NULL, NULL); break; case CMD_MERGE: diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h index faf50265191..19bcbfeea23 100644 --- a/src/include/access/heapam.h +++ b/src/include/access/heapam.h @@ -242,19 +242,22 @@ extern void heap_multi_insert(Relation relation, struct TupleTableSlot **slots, int ntuples, CommandId cid, int options, BulkInsertState bistate); extern TM_Result heap_delete(Relation relation, ItemPointer tid, - CommandId cid, Snapshot crosscheck, bool wait, - struct TM_FailureData *tmfd, bool changingPart); + CommandId cid, Snapshot crosscheck, int options, + struct TM_FailureData *tmfd, bool changingPart, + TupleTableSlot *oldSlot); extern void heap_finish_speculative(Relation relation, ItemPointer tid); extern void heap_abort_speculative(Relation relation, ItemPointer tid); extern TM_Result heap_update(Relation relation, ItemPointer otid, HeapTuple newtup, - CommandId cid, Snapshot crosscheck, bool wait, + CommandId cid, Snapshot crosscheck, int options, struct TM_FailureData *tmfd, LockTupleMode *lockmode, - TU_UpdateIndexes *update_indexes); -extern TM_Result heap_lock_tuple(Relation relation, HeapTuple tuple, - CommandId cid, LockTupleMode mode, LockWaitPolicy wait_policy, - bool follow_updates, - Buffer *buffer, struct TM_FailureData *tmfd); + TU_UpdateIndexes *update_indexes, + TupleTableSlot *oldSlot); +extern TM_Result heap_lock_tuple(Relation relation, ItemPointer tid, + TupleTableSlot *slot, + CommandId cid, LockTupleMode mode, + LockWaitPolicy wait_policy, bool follow_updates, + struct TM_FailureData *tmfd); extern void heap_inplace_update(Relation relation, HeapTuple tuple); extern bool heap_prepare_freeze_tuple(HeapTupleHeader tuple, diff --git a/src/include/access/tableam.h b/src/include/access/tableam.h index 7159365e652..01c2a95d890 100644 --- a/src/include/access/tableam.h +++ b/src/include/access/tableam.h @@ -259,6 +259,11 @@ typedef struct TM_IndexDeleteOp /* Follow update chain and lock latest version of tuple */ #define TUPLE_LOCK_FLAG_FIND_LAST_VERSION (1 << 1) +/* "options" flag bits for table_tuple_update and table_tuple_delete */ +#define TABLE_MODIFY_WAIT 0x0001 +#define TABLE_MODIFY_FETCH_OLD_TUPLE 0x0002 +#define TABLE_MODIFY_LOCK_UPDATED 0x0004 + /* Typedef for callback function for table_index_build_scan */ typedef void (*IndexBuildCallback) (Relation index, @@ -528,10 +533,10 @@ typedef struct TableAmRoutine CommandId cid, Snapshot snapshot, Snapshot crosscheck, - bool wait, + int options, TM_FailureData *tmfd, bool changingPart, - LazyTupleTableSlot *lockedSlot); + TupleTableSlot *oldSlot); /* see table_tuple_update() for reference about parameters */ TM_Result (*tuple_update) (Relation rel, @@ -540,11 +545,11 @@ typedef struct TableAmRoutine CommandId cid, Snapshot snapshot, Snapshot crosscheck, - bool wait, + int options, TM_FailureData *tmfd, LockTupleMode *lockmode, TU_UpdateIndexes *update_indexes, - LazyTupleTableSlot *lockedSlot); + TupleTableSlot *oldSlot); /* see table_tuple_lock() for reference about parameters */ TM_Result (*tuple_lock) (Relation rel, @@ -1459,7 +1464,7 @@ table_multi_insert(Relation rel, TupleTableSlot **slots, int nslots, } /* - * Delete a tuple (or lock last tuple version if lockedSlot is given). + * Delete a tuple (and optionally lock the last tuple version). * * NB: do not call this directly unless prepared to deal with * concurrent-update conditions. Use simple_table_tuple_delete instead. @@ -1470,13 +1475,21 @@ table_multi_insert(Relation rel, TupleTableSlot **slots, int nslots, * cid - delete command ID (used for visibility test, and stored into * cmax if successful) * crosscheck - if not InvalidSnapshot, also check tuple against this - * wait - true if should wait for any conflicting update to commit/abort + * options: + * If TABLE_MODIFY_WAIT, wait for any conflicting update to commit/abort. + * If TABLE_MODIFY_FETCH_OLD_TUPLE option is given, the existing tuple is + * fetched into oldSlot when the update is successful. + * If TABLE_MODIFY_LOCK_UPDATED option is given and the tuple is + * concurrently updated, then the last tuple version is locked and fetched + * into oldSlot. + * * Output parameters: * tmfd - filled in failure cases (see below) * changingPart - true iff the tuple is being moved to another partition * table due to an update of the partition key. Otherwise, false. - * lockedSlot - lazy slot to save the locked tuple if should lock the last - * row version during the concurrent update. NULL if not needed. + * oldSlot - slot to save the deleted or locked tuple. Can be NULL if none of + * TABLE_MODIFY_FETCH_OLD_TUPLE or TABLE_MODIFY_LOCK_UPDATED options + * is specified. * * Normal, successful return value is TM_Ok, which means we did actually * delete it. Failure return codes are TM_SelfModified, TM_Updated, and @@ -1488,18 +1501,18 @@ table_multi_insert(Relation rel, TupleTableSlot **slots, int nslots, */ static inline TM_Result table_tuple_delete(Relation rel, ItemPointer tid, CommandId cid, - Snapshot snapshot, Snapshot crosscheck, bool wait, + Snapshot snapshot, Snapshot crosscheck, int options, TM_FailureData *tmfd, bool changingPart, - LazyTupleTableSlot *lockedSlot) + TupleTableSlot *oldSlot) { return rel->rd_tableam->tuple_delete(rel, tid, cid, snapshot, crosscheck, - wait, tmfd, changingPart, - lockedSlot); + options, tmfd, changingPart, + oldSlot); } /* - * Update a tuple (or lock last tuple version if lockedSlot is given). + * Update a tuple (and optionally lock the last tuple version). * * NB: do not call this directly unless you are prepared to deal with * concurrent-update conditions. Use simple_table_tuple_update instead. @@ -1511,14 +1524,22 @@ table_tuple_delete(Relation rel, ItemPointer tid, CommandId cid, * cid - update command ID (used for visibility test, and stored into * cmax/cmin if successful) * crosscheck - if not InvalidSnapshot, also check old tuple against this - * wait - true if should wait for any conflicting update to commit/abort + * options: + * If TABLE_MODIFY_WAIT, wait for any conflicting update to commit/abort. + * If TABLE_MODIFY_FETCH_OLD_TUPLE option is given, the existing tuple is + * fetched into oldSlot when the update is successful. + * If TABLE_MODIFY_LOCK_UPDATED option is given and the tuple is + * concurrently updated, then the last tuple version is locked and fetched + * into oldSlot. + * * Output parameters: * tmfd - filled in failure cases (see below) * lockmode - filled with lock mode acquired on tuple * update_indexes - in success cases this is set to true if new index entries * are required for this tuple - * lockedSlot - lazy slot to save the locked tuple if should lock the last - * row version during the concurrent update. NULL if not needed. + * oldSlot - slot to save the deleted or locked tuple. Can be NULL if none of + * TABLE_MODIFY_FETCH_OLD_TUPLE or TABLE_MODIFY_LOCK_UPDATED options + * is specified. * Normal, successful return value is TM_Ok, which means we did actually * update it. Failure return codes are TM_SelfModified, TM_Updated, and @@ -1537,15 +1558,15 @@ table_tuple_delete(Relation rel, ItemPointer tid, CommandId cid, static inline TM_Result table_tuple_update(Relation rel, ItemPointer otid, TupleTableSlot *slot, CommandId cid, Snapshot snapshot, Snapshot crosscheck, - bool wait, TM_FailureData *tmfd, LockTupleMode *lockmode, + int options, TM_FailureData *tmfd, LockTupleMode *lockmode, TU_UpdateIndexes *update_indexes, - LazyTupleTableSlot *lockedSlot) + TupleTableSlot *oldSlot) { return rel->rd_tableam->tuple_update(rel, otid, slot, cid, snapshot, crosscheck, - wait, tmfd, + options, tmfd, lockmode, update_indexes, - lockedSlot); + oldSlot); } /* @@ -2061,10 +2082,12 @@ table_scan_sample_next_tuple(TableScanDesc scan, extern void simple_table_tuple_insert(Relation rel, TupleTableSlot *slot); extern void simple_table_tuple_delete(Relation rel, ItemPointer tid, - Snapshot snapshot); + Snapshot snapshot, + TupleTableSlot *oldSlot); extern void simple_table_tuple_update(Relation rel, ItemPointer otid, TupleTableSlot *slot, Snapshot snapshot, - TU_UpdateIndexes *update_indexes); + TU_UpdateIndexes *update_indexes, + TupleTableSlot *oldSlot); /* ---------------------------------------------------------------------------- diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h index 430e3ca7ddf..4903b4b7bc2 100644 --- a/src/include/commands/trigger.h +++ b/src/include/commands/trigger.h @@ -216,8 +216,8 @@ extern bool ExecBRDeleteTriggers(EState *estate, TM_FailureData *tmfd); extern void ExecARDeleteTriggers(EState *estate, ResultRelInfo *relinfo, - ItemPointer tupleid, HeapTuple fdw_trigtuple, + TupleTableSlot *slot, TransitionCaptureState *transition_capture, bool is_crosspart_update); extern bool ExecIRDeleteTriggers(EState *estate, @@ -240,8 +240,8 @@ extern void ExecARUpdateTriggers(EState *estate, ResultRelInfo *relinfo, ResultRelInfo *src_partinfo, ResultRelInfo *dst_partinfo, - ItemPointer tupleid, HeapTuple fdw_trigtuple, + TupleTableSlot *oldslot, TupleTableSlot *newslot, List *recheckIndexes, TransitionCaptureState *transition_capture, diff --git a/src/include/executor/tuptable.h b/src/include/executor/tuptable.h index 2e13ecc3ffe..ff64b7cb98f 100644 --- a/src/include/executor/tuptable.h +++ b/src/include/executor/tuptable.h @@ -300,44 +300,6 @@ typedef struct MinimalTupleTableSlot #define TupIsNull(slot) \ ((slot) == NULL || TTS_EMPTY(slot)) -/*---------- - * LazyTupleTableSlot -- a lazy version of TupleTableSlot. - * - * Sometimes caller might need to pass to the function a slot, which most - * likely will reain undemanded. Preallocating such slot would be a waste of - * resources in the majority of cases. Lazy slot is aimed to resolve this - * problem. It is basically a promise to allocate the slot once it's needed. - * Once callee needs the slot, it could get it using LAZY_TTS_EVAL(lazySlot) - * macro. - */ -typedef struct -{ - TupleTableSlot *slot; /* cached slot or NULL if not yet allocated */ - TupleTableSlot *(*getSlot) (void *arg); /* callback for slot allocation */ - void *getSlotArg; /* argument for the callback above */ -} LazyTupleTableSlot; - -/* - * A constructor for the lazy slot. - */ -#define MAKE_LAZY_TTS(lazySlot, callback, arg) \ - do { \ - (lazySlot)->slot = NULL; \ - (lazySlot)->getSlot = callback; \ - (lazySlot)->getSlotArg = arg; \ - } while (false) - -/* - * Macro for lazy slot evaluation. NULL lazy slot evaluates to NULL slot. - * Cached version is used if present. Use the callback otherwise. - */ -#define LAZY_TTS_EVAL(lazySlot) \ - ((lazySlot) ? \ - ((lazySlot)->slot ? \ - (lazySlot)->slot : \ - ((lazySlot)->slot = (lazySlot)->getSlot((lazySlot)->getSlotArg))) : \ - NULL) - /* in executor/execTuples.c */ extern TupleTableSlot *MakeTupleTableSlot(TupleDesc tupleDesc, const TupleTableSlotOps *tts_ops); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index b97174d1607..5c0410869f7 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -956,7 +956,6 @@ GenerationPointer GenericCosts GenericXLogState GeqoPrivateData -GetEPQSlotArg GetForeignJoinPaths_function GetForeignModifyBatchSize_function GetForeignPaths_function @@ -1402,7 +1401,6 @@ LagTracker LargeObjectDesc LastAttnumInfo Latch -LazyTupleTableSlot LerpFunc LexDescr LexemeEntry -- 2.37.1 (Apple Git-137.1)