diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c index 7f642edf45..4a4cf76269 100644 --- a/src/backend/access/heap/heapam.c +++ b/src/backend/access/heap/heapam.c @@ -2665,11 +2665,10 @@ xmax_infomask_changed(uint16 new_infomask, uint16 old_infomask) } /* - * heap_delete - delete a tuple, optionally fetching it into a slot + * heap_delete - delete a tuple * * See table_tuple_delete() for an explanation of the parameters, except that - * 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. + * this routine directly takes a tuple rather than a slot. * * 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 @@ -2678,9 +2677,8 @@ xmax_infomask_changed(uint16 new_infomask, uint16 old_infomask) */ TM_Result heap_delete(Relation relation, ItemPointer tid, - CommandId cid, Snapshot crosscheck, int options, - TM_FailureData *tmfd, bool changingPart, - TupleTableSlot *oldSlot) + CommandId cid, Snapshot crosscheck, bool wait, + TM_FailureData *tmfd, bool changingPart) { TM_Result result; TransactionId xid = GetCurrentTransactionId(); @@ -2758,7 +2756,7 @@ l1: (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("attempted to delete invisible tuple"))); } - else if (result == TM_BeingModified && (options & TABLE_MODIFY_WAIT)) + else if (result == TM_BeingModified && wait) { TransactionId xwait; uint16 infomask; @@ -2899,30 +2897,7 @@ l1: tmfd->cmax = HeapTupleHeaderGetCmax(tp.t_data); else tmfd->cmax = InvalidCommandId; - - /* - * 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); - } + UnlockReleaseBuffer(buffer); if (have_tuple_lock) UnlockTupleTuplock(relation, &(tp.t_self), LockTupleExclusive); if (vmbuffer != InvalidBuffer) @@ -3096,24 +3071,8 @@ l1: */ CacheInvalidateHeapTuple(relation, &tp, NULL); - /* 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); - } + /* Now we can release the buffer */ + ReleaseBuffer(buffer); /* * Release the lmgr tuple lock, if we had it. @@ -3145,8 +3104,8 @@ simple_heap_delete(Relation relation, ItemPointer tid) result = heap_delete(relation, tid, GetCurrentCommandId(true), InvalidSnapshot, - TABLE_MODIFY_WAIT /* wait for commit */ , - &tmfd, false /* changingPart */ , NULL); + true /* wait for commit */ , + &tmfd, false /* changingPart */ ); switch (result) { case TM_SelfModified: @@ -3173,11 +3132,10 @@ simple_heap_delete(Relation relation, ItemPointer tid) } /* - * heap_update - replace a tuple, optionally fetching it into a slot + * heap_update - replace a tuple * * See table_tuple_update() for an explanation of the parameters, except that - * 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. + * this routine directly takes a tuple rather than a slot. * * 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 @@ -3186,9 +3144,9 @@ simple_heap_delete(Relation relation, ItemPointer tid) */ TM_Result heap_update(Relation relation, ItemPointer otid, HeapTuple newtup, - CommandId cid, Snapshot crosscheck, int options, + CommandId cid, Snapshot crosscheck, bool wait, TM_FailureData *tmfd, LockTupleMode *lockmode, - TU_UpdateIndexes *update_indexes, TupleTableSlot *oldSlot) + TU_UpdateIndexes *update_indexes) { TM_Result result; TransactionId xid = GetCurrentTransactionId(); @@ -3365,7 +3323,7 @@ l2: result = HeapTupleSatisfiesUpdate(&oldtup, cid, buffer); /* see below about the "no wait" case */ - Assert(result != TM_BeingModified || (options & TABLE_MODIFY_WAIT)); + Assert(result != TM_BeingModified || wait); if (result == TM_Invisible) { @@ -3374,7 +3332,7 @@ l2: (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), errmsg("attempted to update invisible tuple"))); } - else if (result == TM_BeingModified && (options & TABLE_MODIFY_WAIT)) + else if (result == TM_BeingModified && wait) { TransactionId xwait; uint16 infomask; @@ -3578,30 +3536,7 @@ l2: tmfd->cmax = HeapTupleHeaderGetCmax(oldtup.t_data); else tmfd->cmax = InvalidCommandId; - - /* - * If we're asked to lock the updated tuple, we just fetch the - * existing tuple. That lets 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 = oldtup; - ExecStorePinnedBufferHeapTuple(&bslot->base.tupdata, - oldSlot, - buffer); - } - else - { - UnlockReleaseBuffer(buffer); - } + UnlockReleaseBuffer(buffer); if (have_tuple_lock) UnlockTupleTuplock(relation, &(oldtup.t_self), *lockmode); if (vmbuffer != InvalidBuffer) @@ -4080,26 +4015,7 @@ l2: /* Now we can release the buffer(s) */ if (newbuf != buffer) ReleaseBuffer(newbuf); - - /* 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); - } - + ReleaseBuffer(buffer); if (BufferIsValid(vmbuffer_new)) ReleaseBuffer(vmbuffer_new); if (BufferIsValid(vmbuffer)) @@ -4307,8 +4223,8 @@ simple_heap_update(Relation relation, ItemPointer otid, HeapTuple tup, result = heap_update(relation, otid, tup, GetCurrentCommandId(true), InvalidSnapshot, - TABLE_MODIFY_WAIT /* wait for commit */ , - &tmfd, &lockmode, update_indexes, NULL); + true /* wait for commit */ , + &tmfd, &lockmode, update_indexes); switch (result) { case TM_SelfModified: @@ -4371,14 +4287,12 @@ get_mxact_status_for_lock(LockTupleMode mode, bool is_update) * tuples. * * Output parameters: - * *slot: BufferHeapTupleTableSlot filled with tuple + * *tuple: all fields filled in + * *buffer: set to buffer holding tuple (pinned but not locked at exit) * *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, @@ -4389,14 +4303,15 @@ 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, ItemPointer tid, TupleTableSlot *slot, +heap_lock_tuple(Relation relation, HeapTuple tuple, CommandId cid, LockTupleMode mode, LockWaitPolicy wait_policy, - bool follow_updates, TM_FailureData *tmfd) + bool follow_updates, + Buffer *buffer, TM_FailureData *tmfd) { TM_Result result; + ItemPointer tid = &(tuple->t_self); ItemId lp; Page page; - Buffer buffer; Buffer vmbuffer = InvalidBuffer; BlockNumber block; TransactionId xid, @@ -4408,24 +4323,8 @@ heap_lock_tuple(Relation relation, ItemPointer tid, TupleTableSlot *slot, 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)); - - /* 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)); - } + *buffer = ReadBuffer(relation, ItemPointerGetBlockNumber(tid)); block = ItemPointerGetBlockNumber(tid); /* @@ -4434,22 +4333,21 @@ heap_lock_tuple(Relation relation, ItemPointer tid, TupleTableSlot *slot, * 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) { @@ -4478,7 +4376,7 @@ 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 @@ -4630,12 +4528,12 @@ 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. @@ -4670,7 +4568,7 @@ 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. @@ -4698,7 +4596,7 @@ 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)) @@ -4710,7 +4608,7 @@ 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) || @@ -4738,7 +4636,7 @@ 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)) @@ -4760,7 +4658,7 @@ 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) @@ -4785,7 +4683,7 @@ l3: */ result = TM_WouldBlock; /* recovery code expects to have buffer lock held */ - LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE); + LockBuffer(*buffer, BUFFER_LOCK_EXCLUSIVE); goto failed; } @@ -4811,7 +4709,7 @@ 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; @@ -4851,7 +4749,7 @@ 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; @@ -4877,12 +4775,12 @@ 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 @@ -4904,7 +4802,7 @@ 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); } } @@ -4963,9 +4861,9 @@ 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; } @@ -5028,7 +4926,7 @@ failed: cleared_all_frozen = true; - MarkBufferDirty(buffer); + MarkBufferDirty(*buffer); /* * XLOG stuff. You might think that we don't need an XLOG record because @@ -5048,7 +4946,7 @@ failed: XLogRecPtr recptr; XLogBeginInsert(); - XLogRegisterBuffer(0, buffer, REGBUF_STANDARD); + XLogRegisterBuffer(0, *buffer, REGBUF_STANDARD); xlrec.offnum = ItemPointerGetOffsetNumber(&tuple->t_self); xlrec.xmax = xid; @@ -5069,7 +4967,7 @@ failed: result = TM_Ok; out_locked: - LockBuffer(buffer, BUFFER_LOCK_UNLOCK); + LockBuffer(*buffer, BUFFER_LOCK_UNLOCK); out_unlocked: if (BufferIsValid(vmbuffer)) @@ -5087,9 +4985,6 @@ 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 00d8270532..cf41ab239e 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -46,11 +46,6 @@ #include "utils/builtins.h" #include "utils/rel.h" -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, Datum *values, bool *isnull, RewriteState rwstate); @@ -306,55 +301,23 @@ heapam_tuple_complete_speculative(Relation relation, TupleTableSlot *slot, static TM_Result heapam_tuple_delete(Relation relation, ItemPointer tid, CommandId cid, - Snapshot snapshot, Snapshot crosscheck, int options, - TM_FailureData *tmfd, bool changingPart, - TupleTableSlot *oldSlot) + Snapshot snapshot, Snapshot crosscheck, bool wait, + TM_FailureData *tmfd, bool changingPart) { - TM_Result result; - /* * Currently Deleting of index tuples are handled at vacuum, in case if * 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, options, - tmfd, changingPart, oldSlot); - - /* - * If the tuple has been concurrently updated, then get the lock on it. - * (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 && (options & TABLE_MODIFY_LOCK_UPDATED)) - { - /* - * 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) - return TM_Updated; - } - - return result; + return heap_delete(relation, tid, cid, crosscheck, wait, tmfd, changingPart); } static TM_Result heapam_tuple_update(Relation relation, ItemPointer otid, TupleTableSlot *slot, CommandId cid, Snapshot snapshot, Snapshot crosscheck, - int options, TM_FailureData *tmfd, - LockTupleMode *lockmode, TU_UpdateIndexes *update_indexes, - TupleTableSlot *oldSlot) + bool wait, TM_FailureData *tmfd, + LockTupleMode *lockmode, TU_UpdateIndexes *update_indexes) { bool shouldFree = true; HeapTuple tuple = ExecFetchSlotHeapTuple(slot, true, &shouldFree); @@ -364,8 +327,8 @@ 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, options, - tmfd, lockmode, update_indexes, oldSlot); + result = heap_update(relation, otid, tuple, cid, crosscheck, wait, + tmfd, lockmode, update_indexes); ItemPointerCopy(&tuple->t_self, &slot->tts_tid); /* @@ -392,31 +355,6 @@ heapam_tuple_update(Relation relation, ItemPointer otid, TupleTableSlot *slot, if (shouldFree) pfree(tuple); - /* - * If the tuple has been concurrently updated, then get the lock on it. - * (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 && (options & TABLE_MODIFY_LOCK_UPDATED)) - { - /* - * 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) - return TM_Updated; - } - return result; } @@ -428,6 +366,7 @@ heapam_tuple_lock(Relation relation, ItemPointer tid, Snapshot snapshot, { BufferHeapTupleTableSlot *bslot = (BufferHeapTupleTableSlot *) slot; TM_Result result; + Buffer buffer; HeapTuple tuple = &bslot->base.tupdata; bool follow_updates; @@ -437,8 +376,9 @@ heapam_tuple_lock(Relation relation, ItemPointer tid, Snapshot snapshot, Assert(TTS_IS_BUFFERTUPLE(slot)); tuple_lock_retry: - result = heap_lock_tuple(relation, tid, slot, cid, mode, wait_policy, - follow_updates, tmfd); + tuple->t_self = *tid; + result = heap_lock_tuple(relation, tuple, cid, mode, wait_policy, + follow_updates, &buffer, tmfd); if (result == TM_Updated && (flags & TUPLE_LOCK_FLAG_FIND_LAST_VERSION)) @@ -446,6 +386,8 @@ tuple_lock_retry: /* Should not encounter speculative tuple on recheck */ Assert(!HeapTupleHeaderIsSpeculative(tuple->t_data)); + ReleaseBuffer(buffer); + if (!ItemPointerEquals(&tmfd->ctid, &tuple->t_self)) { SnapshotData SnapshotDirty; @@ -467,8 +409,6 @@ tuple_lock_retry: InitDirtySnapshot(SnapshotDirty); for (;;) { - Buffer buffer = InvalidBuffer; - if (ItemPointerIndicatesMovedPartitions(tid)) ereport(ERROR, (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE), @@ -563,7 +503,7 @@ tuple_lock_retry: /* * This is a live tuple, so try to lock it again. */ - ExecStorePinnedBufferHeapTuple(tuple, slot, buffer); + ReleaseBuffer(buffer); goto tuple_lock_retry; } @@ -574,7 +514,7 @@ tuple_lock_retry: */ if (tuple->t_data == NULL) { - ReleaseBuffer(buffer); + Assert(!BufferIsValid(buffer)); return TM_Deleted; } @@ -627,6 +567,9 @@ 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 8d3675be95..e57a0b7ea3 100644 --- a/src/backend/access/table/tableam.c +++ b/src/backend/access/table/tableam.c @@ -287,23 +287,16 @@ simple_table_tuple_insert(Relation rel, TupleTableSlot *slot) * via ereport(). */ void -simple_table_tuple_delete(Relation rel, ItemPointer tid, Snapshot snapshot, - TupleTableSlot *oldSlot) +simple_table_tuple_delete(Relation rel, ItemPointer tid, Snapshot snapshot) { 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, - options, - &tmfd, false /* changingPart */ , - oldSlot); + true /* wait for commit */ , + &tmfd, false /* changingPart */ ); switch (result) { @@ -342,24 +335,17 @@ void simple_table_tuple_update(Relation rel, ItemPointer otid, TupleTableSlot *slot, Snapshot snapshot, - TU_UpdateIndexes *update_indexes, - TupleTableSlot *oldSlot) + TU_UpdateIndexes *update_indexes) { 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, - options, - &tmfd, &lockmode, update_indexes, - oldSlot); + true /* wait for commit */ , + &tmfd, &lockmode, update_indexes); switch (result) { diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c index 84494c4b81..35eb7180f7 100644 --- a/src/backend/commands/trigger.c +++ b/src/backend/commands/trigger.c @@ -2773,8 +2773,8 @@ 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) { @@ -2783,11 +2783,20 @@ ExecARDeleteTriggers(EState *estate, if ((trigdesc && trigdesc->trig_delete_after_row) || (transition_capture && transition_capture->tcs_delete_old_table)) { - /* - * Put the FDW old tuple to the slot. Otherwise, the caller is - * expected to have an old tuple already fetched to the slot. - */ - if (fdw_trigtuple != NULL) + 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 ExecForceStoreHeapTuple(fdw_trigtuple, slot, false); AfterTriggerSaveEvent(estate, relinfo, NULL, NULL, @@ -3078,17 +3087,18 @@ 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'. - * '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. + * '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. */ 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, @@ -3107,14 +3117,29 @@ 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); - if (fdw_trigtuple != NULL) - { - Assert(oldslot); + 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) 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 0cad843fb6..d0a89cd577 100644 --- a/src/backend/executor/execReplication.c +++ b/src/backend/executor/execReplication.c @@ -577,7 +577,6 @@ ExecSimpleRelationUpdate(ResultRelInfo *resultRelInfo, { List *recheckIndexes = NIL; TU_UpdateIndexes update_indexes; - TupleTableSlot *oldSlot = NULL; /* Compute stored generated columns */ if (rel->rd_att->constr && @@ -591,12 +590,8 @@ 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, oldSlot); + &update_indexes); if (resultRelInfo->ri_NumIndices > 0 && (update_indexes != TU_None)) recheckIndexes = ExecInsertIndexTuples(resultRelInfo, @@ -607,7 +602,7 @@ ExecSimpleRelationUpdate(ResultRelInfo *resultRelInfo, /* AFTER ROW UPDATE Triggers */ ExecARUpdateTriggers(estate, resultRelInfo, NULL, NULL, - NULL, oldSlot, slot, + tid, NULL, slot, recheckIndexes, NULL, false); list_free(recheckIndexes); @@ -641,18 +636,12 @@ 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, oldSlot); + simple_table_tuple_delete(rel, tid, estate->es_snapshot); /* AFTER ROW DELETE Triggers */ ExecARDeleteTriggers(estate, resultRelInfo, - NULL, oldSlot, NULL, false); + tid, NULL, NULL, false); } } diff --git a/src/backend/executor/nodeModifyTable.c b/src/backend/executor/nodeModifyTable.c index 325d380b0a..c570965da0 100644 --- a/src/backend/executor/nodeModifyTable.c +++ b/src/backend/executor/nodeModifyTable.c @@ -568,15 +568,6 @@ ExecInitInsertProjection(ModifyTableState *mtstate, table_slot_create(resultRelInfo->ri_RelationDesc, &estate->es_tupleTable); - /* - * In the ON CONFLICT UPDATE case, we will also need a slot for the old - * tuple to calculate the updated tuple on its base. - */ - 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) { @@ -1165,7 +1156,7 @@ ExecInsert(ModifyTableContext *context, ExecARUpdateTriggers(estate, resultRelInfo, NULL, NULL, NULL, - resultRelInfo->ri_oldTupleSlot, + NULL, slot, NULL, mtstate->mt_transition_capture, @@ -1345,8 +1336,7 @@ ExecDeletePrologue(ModifyTableContext *context, ResultRelInfo *resultRelInfo, */ static TM_Result ExecDeleteAct(ModifyTableContext *context, ResultRelInfo *resultRelInfo, - ItemPointer tupleid, bool changingPart, int options, - TupleTableSlot *oldSlot) + ItemPointer tupleid, bool changingPart) { EState *estate = context->estate; @@ -1354,10 +1344,9 @@ ExecDeleteAct(ModifyTableContext *context, ResultRelInfo *resultRelInfo, estate->es_output_cid, estate->es_snapshot, estate->es_crosscheck_snapshot, - options, + true /* wait for commit */ , &context->tmfd, - changingPart, - oldSlot); + changingPart); } /* @@ -1366,15 +1355,10 @@ ExecDeleteAct(ModifyTableContext *context, ResultRelInfo *resultRelInfo, * Closing steps of tuple deletion; this invokes AFTER FOR EACH ROW triggers, * including the UPDATE triggers if the deletion is being done as part of a * cross-partition tuple move. - * - * The old tuple is already fetched into ‘slot’ for regular tables. For FDW, - * the old tuple is given as 'oldtuple' and is to be stored in 'slot' when - * needed. */ static void ExecDeleteEpilogue(ModifyTableContext *context, ResultRelInfo *resultRelInfo, - ItemPointer tupleid, HeapTuple oldtuple, - TupleTableSlot *slot, bool changingPart) + ItemPointer tupleid, HeapTuple oldtuple, bool changingPart) { ModifyTableState *mtstate = context->mtstate; EState *estate = context->estate; @@ -1392,8 +1376,8 @@ ExecDeleteEpilogue(ModifyTableContext *context, ResultRelInfo *resultRelInfo, { ExecARUpdateTriggers(estate, resultRelInfo, NULL, NULL, - oldtuple, - slot, NULL, NULL, mtstate->mt_transition_capture, + tupleid, oldtuple, + NULL, NULL, mtstate->mt_transition_capture, false); /* @@ -1404,30 +1388,10 @@ ExecDeleteEpilogue(ModifyTableContext *context, ResultRelInfo *resultRelInfo, } /* AFTER ROW DELETE Triggers */ - ExecARDeleteTriggers(estate, resultRelInfo, oldtuple, slot, + ExecARDeleteTriggers(estate, resultRelInfo, tupleid, oldtuple, 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 * @@ -1447,8 +1411,7 @@ ExecInitDeleteTupleSlot(ModifyTableState *mtstate, * part of an UPDATE of partition-key, then the slot returned by * EvalPlanQual() is passed back using output parameter epqreturnslot. * - * Returns RETURNING result if any, otherwise NULL. The deleted tuple - * to be stored into oldslot independently that. + * Returns RETURNING result if any, otherwise NULL. * ---------------------------------------------------------------- */ static TupleTableSlot * @@ -1456,7 +1419,6 @@ ExecDelete(ModifyTableContext *context, ResultRelInfo *resultRelInfo, ItemPointer tupleid, HeapTuple oldtuple, - TupleTableSlot *oldslot, bool processReturning, bool changingPart, bool canSetTag, @@ -1520,15 +1482,6 @@ ExecDelete(ModifyTableContext *context, } else { - int options = TABLE_MODIFY_WAIT | TABLE_MODIFY_FETCH_OLD_TUPLE; - - /* - * Specify that we need to lock and fetch the last tuple version for - * EPQ on appropriate transaction isolation levels. - */ - if (!IsolationUsesXactSnapshot()) - options |= TABLE_MODIFY_LOCK_UPDATED; - /* * delete the tuple * @@ -1539,8 +1492,7 @@ ExecDelete(ModifyTableContext *context, * transaction-snapshot mode transactions. */ ldelete: - result = ExecDeleteAct(context, resultRelInfo, tupleid, changingPart, - options, oldslot); + result = ExecDeleteAct(context, resultRelInfo, tupleid, changingPart); if (tmresult) *tmresult = result; @@ -1587,6 +1539,7 @@ ldelete: case TM_Updated: { + TupleTableSlot *inputslot; TupleTableSlot *epqslot; if (IsolationUsesXactSnapshot()) @@ -1595,29 +1548,87 @@ ldelete: errmsg("could not serialize access due to concurrent update"))); /* - * We need to do EPQ. The latest tuple is already found - * and locked as a result of TABLE_MODIFY_LOCK_UPDATED. + * Already know that we're going to need to do EPQ, so + * fetch tuple directly into the right slot. */ - Assert(context->tmfd.traversed); - epqslot = EvalPlanQual(context->epqstate, - resultRelationDesc, - resultRelInfo->ri_RangeTableIndex, - oldslot); - if (TupIsNull(epqslot)) - /* Tuple not passing quals anymore, exiting... */ - return NULL; + EvalPlanQualBegin(context->epqstate); + inputslot = EvalPlanQualSlot(context->epqstate, resultRelationDesc, + resultRelInfo->ri_RangeTableIndex); - /* - * If requested, skip delete and pass back the updated - * row. - */ - if (epqreturnslot) + result = table_tuple_lock(resultRelationDesc, tupleid, + estate->es_snapshot, + inputslot, estate->es_output_cid, + LockTupleExclusive, LockWaitBlock, + TUPLE_LOCK_FLAG_FIND_LAST_VERSION, + &context->tmfd); + + switch (result) { - *epqreturnslot = epqslot; - return NULL; + case TM_Ok: + Assert(context->tmfd.traversed); + epqslot = EvalPlanQual(context->epqstate, + resultRelationDesc, + resultRelInfo->ri_RangeTableIndex, + inputslot); + if (TupIsNull(epqslot)) + /* Tuple not passing quals anymore, exiting... */ + return NULL; + + /* + * If requested, skip delete and pass back the + * updated row. + */ + if (epqreturnslot) + { + *epqreturnslot = epqslot; + return NULL; + } + else + goto ldelete; + + case TM_SelfModified: + + /* + * This can be reached when following an update + * chain from a tuple updated by another session, + * reaching a tuple that was already updated in + * this transaction. If previously updated by this + * command, ignore the delete, otherwise error + * out. + * + * See also TM_SelfModified response to + * table_tuple_delete() above. + */ + if (context->tmfd.cmax != estate->es_output_cid) + ereport(ERROR, + (errcode(ERRCODE_TRIGGERED_DATA_CHANGE_VIOLATION), + errmsg("tuple to be deleted was already modified by an operation triggered by the current command"), + errhint("Consider using an AFTER trigger instead of a BEFORE trigger to propagate changes to other rows."))); + return NULL; + + case TM_Deleted: + /* tuple already deleted; nothing to do */ + return NULL; + + default: + + /* + * TM_Invisible should be impossible because we're + * waiting for updated row versions, and would + * already have errored out if the first version + * is invisible. + * + * TM_Updated should be impossible, because we're + * locking the latest version via + * TUPLE_LOCK_FLAG_FIND_LAST_VERSION. + */ + elog(ERROR, "unexpected table_tuple_lock status: %u", + result); + return NULL; } - else - goto ldelete; + + Assert(false); + break; } case TM_Deleted: @@ -1651,8 +1662,7 @@ ldelete: if (tupleDeleted) *tupleDeleted = true; - ExecDeleteEpilogue(context, resultRelInfo, tupleid, oldtuple, - oldslot, changingPart); + ExecDeleteEpilogue(context, resultRelInfo, tupleid, oldtuple, changingPart); /* Process RETURNING if present and if requested */ if (processReturning && resultRelInfo->ri_projectReturning) @@ -1670,13 +1680,17 @@ ldelete: } else { - /* Copy old tuple to the returning slot */ slot = ExecGetReturningSlot(estate, resultRelInfo); if (oldtuple != NULL) + { ExecForceStoreHeapTuple(oldtuple, slot, false); + } else - ExecCopySlot(slot, oldslot); - Assert(!TupIsNull(slot)); + { + if (!table_tuple_fetch_row_version(resultRelationDesc, tupleid, + SnapshotAny, slot)) + elog(ERROR, "failed to fetch deleted tuple for DELETE RETURNING"); + } } rslot = ExecProcessReturning(resultRelInfo, slot, context->planSlot); @@ -1776,19 +1790,12 @@ ExecCrossPartitionUpdate(ModifyTableContext *context, MemoryContextSwitchTo(oldcxt); } - /* - * Make sure ri_oldTupleSlot is initialized. The old tuple is to be saved - * there by ExecDelete() to save effort on further re-fetching. - */ - 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, resultRelInfo->ri_oldTupleSlot, + tupleid, oldtuple, false, /* processReturning */ true, /* changingPart */ false, /* canSetTag */ @@ -1829,13 +1836,21 @@ ExecCrossPartitionUpdate(ModifyTableContext *context, return true; else { - /* - * ExecDelete already fetches the most recent version of old tuple - * to resultRelInfo->ri_oldTupleSlot. So, just project the new - * tuple to retry the UPDATE with. - */ + /* 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 */ *retry_slot = ExecGetUpdateNewTuple(resultRelInfo, epqslot, - resultRelInfo->ri_oldTupleSlot); + oldSlot); return false; } } @@ -1954,8 +1969,7 @@ ExecUpdatePrepareSlot(ResultRelInfo *resultRelInfo, static TM_Result ExecUpdateAct(ModifyTableContext *context, ResultRelInfo *resultRelInfo, ItemPointer tupleid, HeapTuple oldtuple, TupleTableSlot *slot, - bool canSetTag, int options, TupleTableSlot *oldSlot, - UpdateContext *updateCxt) + bool canSetTag, UpdateContext *updateCxt) { EState *estate = context->estate; Relation resultRelationDesc = resultRelInfo->ri_RelationDesc; @@ -2047,8 +2061,7 @@ lreplace: ExecCrossPartitionUpdateForeignKey(context, resultRelInfo, insert_destrel, - tupleid, - resultRelInfo->ri_oldTupleSlot, + tupleid, slot, inserted_tuple); return TM_Ok; @@ -2091,10 +2104,9 @@ lreplace: estate->es_output_cid, estate->es_snapshot, estate->es_crosscheck_snapshot, - options /* wait for commit */ , + true /* wait for commit */ , &context->tmfd, &updateCxt->lockmode, - &updateCxt->updateIndexes, - oldSlot); + &updateCxt->updateIndexes); return result; } @@ -2108,8 +2120,7 @@ lreplace: static void ExecUpdateEpilogue(ModifyTableContext *context, UpdateContext *updateCxt, ResultRelInfo *resultRelInfo, ItemPointer tupleid, - HeapTuple oldtuple, TupleTableSlot *slot, - TupleTableSlot *oldslot) + HeapTuple oldtuple, TupleTableSlot *slot) { ModifyTableState *mtstate = context->mtstate; List *recheckIndexes = NIL; @@ -2125,7 +2136,7 @@ ExecUpdateEpilogue(ModifyTableContext *context, UpdateContext *updateCxt, /* AFTER ROW UPDATE Triggers */ ExecARUpdateTriggers(context->estate, resultRelInfo, NULL, NULL, - oldtuple, oldslot, slot, + tupleid, oldtuple, slot, recheckIndexes, mtstate->operation == CMD_INSERT ? mtstate->mt_oc_transition_capture : @@ -2214,7 +2225,7 @@ ExecCrossPartitionUpdateForeignKey(ModifyTableContext *context, /* Perform the root table's triggers. */ ExecARUpdateTriggers(context->estate, rootRelInfo, sourcePartInfo, destPartInfo, - NULL, oldslot, newslot, NIL, NULL, true); + tupleid, NULL, newslot, NIL, NULL, true); } /* ---------------------------------------------------------------- @@ -2237,7 +2248,6 @@ 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. @@ -2248,7 +2258,7 @@ ExecCrossPartitionUpdateForeignKey(ModifyTableContext *context, static TupleTableSlot * ExecUpdate(ModifyTableContext *context, ResultRelInfo *resultRelInfo, ItemPointer tupleid, HeapTuple oldtuple, TupleTableSlot *slot, - TupleTableSlot *oldslot, bool canSetTag, bool locked) + bool canSetTag) { EState *estate = context->estate; Relation resultRelationDesc = resultRelInfo->ri_RelationDesc; @@ -2301,16 +2311,6 @@ ExecUpdate(ModifyTableContext *context, ResultRelInfo *resultRelInfo, } else { - int options = TABLE_MODIFY_WAIT | TABLE_MODIFY_FETCH_OLD_TUPLE; - - /* - * Specify that we need to lock and fetch the last tuple version for - * EPQ on appropriate transaction isolation levels if the tuple isn't - * locked already. - */ - 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, @@ -2320,7 +2320,7 @@ ExecUpdate(ModifyTableContext *context, ResultRelInfo *resultRelInfo, */ redo_act: result = ExecUpdateAct(context, resultRelInfo, tupleid, oldtuple, slot, - canSetTag, options, oldslot, &updateCxt); + canSetTag, &updateCxt); /* * If ExecUpdateAct reports that a cross-partition update was done, @@ -2371,32 +2371,88 @@ redo_act: case TM_Updated: { + TupleTableSlot *inputslot; TupleTableSlot *epqslot; + TupleTableSlot *oldSlot; if (IsolationUsesXactSnapshot()) ereport(ERROR, (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE), errmsg("could not serialize access due to concurrent update"))); - /* Shouldn't get there if the tuple was previously locked */ - Assert(!locked); - /* - * We need to do EPQ. The latest tuple is already found - * and locked as a result of TABLE_MODIFY_LOCK_UPDATED. + * Already know that we're going to need to do EPQ, so + * fetch tuple directly into the right slot. */ - Assert(context->tmfd.traversed); - epqslot = EvalPlanQual(context->epqstate, - resultRelationDesc, - resultRelInfo->ri_RangeTableIndex, - oldslot); - if (TupIsNull(epqslot)) - /* Tuple not passing quals anymore, exiting... */ - return NULL; - slot = ExecGetUpdateNewTuple(resultRelInfo, - epqslot, - oldslot); - goto redo_act; + inputslot = EvalPlanQualSlot(context->epqstate, resultRelationDesc, + resultRelInfo->ri_RangeTableIndex); + + result = table_tuple_lock(resultRelationDesc, tupleid, + estate->es_snapshot, + inputslot, estate->es_output_cid, + updateCxt.lockmode, LockWaitBlock, + TUPLE_LOCK_FLAG_FIND_LAST_VERSION, + &context->tmfd); + + switch (result) + { + case TM_Ok: + Assert(context->tmfd.traversed); + + epqslot = EvalPlanQual(context->epqstate, + resultRelationDesc, + resultRelInfo->ri_RangeTableIndex, + inputslot); + if (TupIsNull(epqslot)) + /* Tuple not passing quals anymore, exiting... */ + return NULL; + + /* Make sure ri_oldTupleSlot is initialized. */ + if (unlikely(!resultRelInfo->ri_projectNewInfoValid)) + ExecInitUpdateProjection(context->mtstate, + resultRelInfo); + + /* Fetch the most recent version of old tuple. */ + oldSlot = resultRelInfo->ri_oldTupleSlot; + if (!table_tuple_fetch_row_version(resultRelationDesc, + tupleid, + SnapshotAny, + oldSlot)) + elog(ERROR, "failed to fetch tuple being updated"); + slot = ExecGetUpdateNewTuple(resultRelInfo, + epqslot, oldSlot); + goto redo_act; + + case TM_Deleted: + /* tuple already deleted; nothing to do */ + return NULL; + + case TM_SelfModified: + + /* + * This can be reached when following an update + * chain from a tuple updated by another session, + * reaching a tuple that was already updated in + * this transaction. If previously modified by + * this command, ignore the redundant update, + * otherwise error out. + * + * See also TM_SelfModified response to + * table_tuple_update() above. + */ + if (context->tmfd.cmax != estate->es_output_cid) + ereport(ERROR, + (errcode(ERRCODE_TRIGGERED_DATA_CHANGE_VIOLATION), + errmsg("tuple to be updated was already modified by an operation triggered by the current command"), + errhint("Consider using an AFTER trigger instead of a BEFORE trigger to propagate changes to other rows."))); + return NULL; + + default: + /* see table_tuple_lock call in ExecDelete() */ + elog(ERROR, "unexpected table_tuple_lock status: %u", + result); + return NULL; + } } break; @@ -2420,7 +2476,7 @@ redo_act: (estate->es_processed)++; ExecUpdateEpilogue(context, &updateCxt, resultRelInfo, tupleid, oldtuple, - slot, oldslot); + slot); /* Process RETURNING if present */ if (resultRelInfo->ri_projectReturning) @@ -2638,8 +2694,7 @@ ExecOnConflictUpdate(ModifyTableContext *context, *returning = ExecUpdate(context, resultRelInfo, conflictTid, NULL, resultRelInfo->ri_onConflict->oc_ProjSlot, - existing, - canSetTag, true); + canSetTag); /* * Clear out existing tuple, as there might not be another conflict among @@ -2918,7 +2973,6 @@ lmerge_matched: { result = ExecUpdateAct(context, resultRelInfo, tupleid, NULL, newslot, canSetTag, - TABLE_MODIFY_WAIT, NULL, &updateCxt); /* @@ -2940,8 +2994,7 @@ lmerge_matched: if (result == TM_Ok) { ExecUpdateEpilogue(context, &updateCxt, resultRelInfo, - tupleid, NULL, newslot, - resultRelInfo->ri_oldTupleSlot); + tupleid, NULL, newslot); mtstate->mt_merge_updated += 1; } break; @@ -2967,12 +3020,12 @@ lmerge_matched: } else result = ExecDeleteAct(context, resultRelInfo, tupleid, - false, TABLE_MODIFY_WAIT, NULL); + false); if (result == TM_Ok) { ExecDeleteEpilogue(context, resultRelInfo, tupleid, NULL, - resultRelInfo->ri_oldTupleSlot, false); + false); mtstate->mt_merge_deleted += 1; } break; @@ -4037,18 +4090,12 @@ ExecModifyTable(PlanState *pstate) /* Now apply the update. */ slot = ExecUpdate(&context, resultRelInfo, tupleid, oldtuple, - slot, resultRelInfo->ri_oldTupleSlot, - node->canSetTag, false); + slot, node->canSetTag); 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, - resultRelInfo->ri_oldTupleSlot, true, false, - node->canSetTag, NULL, NULL, NULL); + true, false, node->canSetTag, NULL, NULL, NULL); break; case CMD_MERGE: diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h index 3abe226bd5..735662dc9d 100644 --- a/src/include/access/heapam.h +++ b/src/include/access/heapam.h @@ -322,22 +322,19 @@ 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, int options, - struct TM_FailureData *tmfd, bool changingPart, - TupleTableSlot *oldSlot); + CommandId cid, Snapshot crosscheck, bool wait, + struct TM_FailureData *tmfd, bool changingPart); 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, int options, + CommandId cid, Snapshot crosscheck, bool wait, struct TM_FailureData *tmfd, LockTupleMode *lockmode, - 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); + 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); 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 00deb36f5a..6ef7714d2b 100644 --- a/src/include/access/tableam.h +++ b/src/include/access/tableam.h @@ -267,15 +267,6 @@ 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, - * Wait for any conflicting update to commit/abort */ -#define TABLE_MODIFY_WAIT 0x0001 -/* Fetch the existing tuple into a dedicated slot */ -#define TABLE_MODIFY_FETCH_OLD_TUPLE 0x0002 -/* On concurrent update, follow the update chain and lock latest version of tuple */ -#define TABLE_MODIFY_LOCK_UPDATED 0x0004 - /* Typedef for callback function for table_index_build_scan */ typedef void (*IndexBuildCallback) (Relation index, @@ -545,10 +536,9 @@ typedef struct TableAmRoutine CommandId cid, Snapshot snapshot, Snapshot crosscheck, - int options, + bool wait, TM_FailureData *tmfd, - bool changingPart, - TupleTableSlot *oldSlot); + bool changingPart); /* see table_tuple_update() for reference about parameters */ TM_Result (*tuple_update) (Relation rel, @@ -557,11 +547,10 @@ typedef struct TableAmRoutine CommandId cid, Snapshot snapshot, Snapshot crosscheck, - int options, + bool wait, TM_FailureData *tmfd, LockTupleMode *lockmode, - TU_UpdateIndexes *update_indexes, - TupleTableSlot *oldSlot); + TU_UpdateIndexes *update_indexes); /* see table_tuple_lock() for reference about parameters */ TM_Result (*tuple_lock) (Relation rel, @@ -1456,7 +1445,7 @@ table_multi_insert(Relation rel, TupleTableSlot **slots, int nslots, } /* - * Delete a tuple (and optionally lock the last tuple version). + * Delete a tuple. * * NB: do not call this directly unless prepared to deal with * concurrent-update conditions. Use simple_table_tuple_delete instead. @@ -1467,21 +1456,11 @@ 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 - * 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. - * + * wait - true if should wait for any conflicting update to commit/abort * 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. - * 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 @@ -1493,18 +1472,16 @@ 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, int options, - TM_FailureData *tmfd, bool changingPart, - TupleTableSlot *oldSlot) + Snapshot snapshot, Snapshot crosscheck, bool wait, + TM_FailureData *tmfd, bool changingPart) { return rel->rd_tableam->tuple_delete(rel, tid, cid, snapshot, crosscheck, - options, tmfd, changingPart, - oldSlot); + wait, tmfd, changingPart); } /* - * Update a tuple (and optionally lock the last tuple version). + * Update a tuple. * * NB: do not call this directly unless you are prepared to deal with * concurrent-update conditions. Use simple_table_tuple_update instead. @@ -1516,23 +1493,13 @@ 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 - * 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. - * + * wait - true if should wait for any conflicting update to commit/abort * 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 - * 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 * TM_BeingModified (the last only possible if wait == false). @@ -1550,15 +1517,13 @@ 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, - int options, TM_FailureData *tmfd, LockTupleMode *lockmode, - TU_UpdateIndexes *update_indexes, - TupleTableSlot *oldSlot) + bool wait, TM_FailureData *tmfd, LockTupleMode *lockmode, + TU_UpdateIndexes *update_indexes) { return rel->rd_tableam->tuple_update(rel, otid, slot, cid, snapshot, crosscheck, - options, tmfd, - lockmode, update_indexes, - oldSlot); + wait, tmfd, + lockmode, update_indexes); } /* @@ -2079,12 +2044,10 @@ 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, - TupleTableSlot *oldSlot); + Snapshot snapshot); extern void simple_table_tuple_update(Relation rel, ItemPointer otid, TupleTableSlot *slot, Snapshot snapshot, - TU_UpdateIndexes *update_indexes, - TupleTableSlot *oldSlot); + TU_UpdateIndexes *update_indexes); /* ---------------------------------------------------------------------------- diff --git a/src/include/commands/trigger.h b/src/include/commands/trigger.h index cb968d03ec..8a5a9fe642 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,