heapam.c

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

		if (infomask & HEAP_XMAX_IS_MULTI)
		{
			/* wait for multixact */
			MultiXactIdWait((MultiXactId) xwait);
			LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);

			/*
			 * If xwait had just locked the tuple then some other xact could
			 * update this tuple before we get to this point.  Check for xmax
			 * change, and start over if so.
			 */
			if (!(tp.t_data->t_infomask & HEAP_XMAX_IS_MULTI) ||
				!TransactionIdEquals(HeapTupleHeaderGetXmax(tp.t_data),
									 xwait))
				goto l1;

			/*
			 * You might think the multixact is necessarily done here, but not
			 * so: it could have surviving members, namely our own xact or
			 * other subxacts of this backend.	It is legal for us to delete
			 * the tuple in either case, however (the latter case is
			 * essentially a situation of upgrading our former shared lock to
			 * exclusive).	We don't bother changing the on-disk hint bits
			 * since we are about to overwrite the xmax altogether.
			 */
		}
		else
		{
			/* wait for regular transaction to end */
			XactLockTableWait(xwait);
			LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);

			/*
			 * xwait is done, but if xwait had just locked the tuple then some
			 * other xact could update this tuple before we get to this point.
			 * Check for xmax change, and start over if so.
			 */
			if ((tp.t_data->t_infomask & HEAP_XMAX_IS_MULTI) ||
				!TransactionIdEquals(HeapTupleHeaderGetXmax(tp.t_data),
									 xwait))
				goto l1;

			/* Otherwise we can mark it committed or aborted */
			if (!(tp.t_data->t_infomask & (HEAP_XMAX_COMMITTED |
										   HEAP_XMAX_INVALID)))
			{
				if (TransactionIdDidCommit(xwait))
					tp.t_data->t_infomask |= HEAP_XMAX_COMMITTED;
				else
					tp.t_data->t_infomask |= HEAP_XMAX_INVALID;
				SetBufferCommitInfoNeedsSave(buffer);
			}
		}

		/*
		 * We may overwrite if previous xmax aborted, or if it committed but
		 * only locked the tuple without updating it.
		 */
		if (tp.t_data->t_infomask & (HEAP_XMAX_INVALID |
									 HEAP_IS_LOCKED))
			result = HeapTupleMayBeUpdated;
		else
			result = HeapTupleUpdated;
	}

	if (crosscheck != InvalidSnapshot && result == HeapTupleMayBeUpdated)
	{
		/* Perform additional check for serializable RI updates */
		if (!HeapTupleSatisfiesSnapshot(tp.t_data, crosscheck, buffer))
			result = HeapTupleUpdated;
	}

	if (result != HeapTupleMayBeUpdated)
	{
		Assert(result == HeapTupleSelfUpdated ||
			   result == HeapTupleUpdated ||
			   result == HeapTupleBeingUpdated);
		Assert(!(tp.t_data->t_infomask & HEAP_XMAX_INVALID));
		*ctid = tp.t_data->t_ctid;
		*update_xmax = HeapTupleHeaderGetXmax(tp.t_data);
		LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
		ReleaseBuffer(buffer);
		if (have_tuple_lock)
			UnlockTuple(relation, &(tp.t_self), ExclusiveLock);
		return result;
	}

	START_CRIT_SECTION();

	/* store transaction information of xact deleting the tuple */
	tp.t_data->t_infomask &= ~(HEAP_XMAX_COMMITTED |
							   HEAP_XMAX_INVALID |
							   HEAP_XMAX_IS_MULTI |
							   HEAP_IS_LOCKED |
							   HEAP_MOVED);
	HeapTupleHeaderSetXmax(tp.t_data, xid);
	HeapTupleHeaderSetCmax(tp.t_data, cid);
	/* Make sure there is no forward chain link in t_ctid */
	tp.t_data->t_ctid = tp.t_self;

	/* XLOG stuff */
	if (!relation->rd_istemp)
	{
		xl_heap_delete xlrec;
		XLogRecPtr	recptr;
		XLogRecData rdata[2];

		xlrec.target.node = relation->rd_node;
		xlrec.target.tid = tp.t_self;
		rdata[0].data = (char *) &xlrec;
		rdata[0].len = SizeOfHeapDelete;
		rdata[0].buffer = InvalidBuffer;
		rdata[0].next = &(rdata[1]);

		rdata[1].data = NULL;
		rdata[1].len = 0;
		rdata[1].buffer = buffer;
		rdata[1].buffer_std = true;
		rdata[1].next = NULL;

		recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_DELETE, rdata);

		PageSetLSN(dp, recptr);
		PageSetTLI(dp, ThisTimeLineID);
	}
	else
	{
		/* No XLOG record, but still need to flag that XID exists on disk */
		MyXactMadeTempRelUpdate = true;
	}

	END_CRIT_SECTION();

	LockBuffer(buffer, BUFFER_LOCK_UNLOCK);

	/*
	 * If the tuple has toasted out-of-line attributes, we need to delete
	 * those items too.  We have to do this before WriteBuffer because we need
	 * to look at the contents of the tuple, but it's OK to release the
	 * context lock on the buffer first.
	 */
	if (HeapTupleHasExternal(&tp))
		toast_delete(relation, &tp);

	/*
	 * Mark tuple for invalidation from system caches at next command
	 * boundary. We have to do this before WriteBuffer because we need to look
	 * at the contents of the tuple, so we need to hold our refcount on the
	 * buffer.
	 */
	CacheInvalidateHeapTuple(relation, &tp);

	WriteBuffer(buffer);

	/*
	 * Release the lmgr tuple lock, if we had it.
	 */
	if (have_tuple_lock)
		UnlockTuple(relation, &(tp.t_self), ExclusiveLock);

	pgstat_count_heap_delete(&relation->pgstat_info);

	return HeapTupleMayBeUpdated;
}

/*
 *	simple_heap_delete - delete a tuple
 *
 * This routine may be used to delete a tuple when concurrent updates of
 * the target tuple are not expected (for example, because we have a lock
 * on the relation associated with the tuple).	Any failure is reported
 * via ereport().
 */
void
simple_heap_delete(Relation relation, ItemPointer tid)
{
	HTSU_Result result;
	ItemPointerData update_ctid;
	TransactionId update_xmax;

	result = heap_delete(relation, tid,
						 &update_ctid, &update_xmax,
						 GetCurrentCommandId(), InvalidSnapshot,
						 true /* wait for commit */ );
	switch (result)
	{
		case HeapTupleSelfUpdated:
			/* Tuple was already updated in current command? */
			elog(ERROR, "tuple already updated by self");
			break;

		case HeapTupleMayBeUpdated:
			/* done successfully */
			break;

		case HeapTupleUpdated:
			elog(ERROR, "tuple concurrently updated");
			break;

		default:
			elog(ERROR, "unrecognized heap_delete status: %u", result);
			break;
	}
}

/*
 *	heap_update - replace a tuple
 *
 * NB: do not call this directly unless you are prepared to deal with
 * concurrent-update conditions.  Use simple_heap_update instead.
 *
 *	relation - table to be modified (caller must hold suitable lock)
 *	otid - TID of old tuple to be replaced
 *	newtup - newly constructed tuple data to store
 *	ctid - output parameter, used only for failure case (see below)
 *	update_xmax - output parameter, used only for failure case (see below)
 *	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
 *
 * Normal, successful return value is HeapTupleMayBeUpdated, which
 * actually means we *did* update it.  Failure return codes are
 * HeapTupleSelfUpdated, HeapTupleUpdated, or HeapTupleBeingUpdated
 * (the last only possible if wait == false).
 *
 * On success, the header fields of *newtup are updated to match the new
 * stored tuple; in particular, newtup->t_self is set to the TID where the
 * new tuple was inserted.	However, any TOAST changes in the new tuple's
 * data are not reflected into *newtup.
 *
 * In the failure cases, the routine returns the tuple's t_ctid and t_xmax.
 * If t_ctid is the same as otid, the tuple was deleted; if different, the
 * tuple was updated, and t_ctid is the location of the replacement tuple.
 * (t_xmax is needed to verify that the replacement tuple matches.)
 */
HTSU_Result
heap_update(Relation relation, ItemPointer otid, HeapTuple newtup,
			ItemPointer ctid, TransactionId *update_xmax,
			CommandId cid, Snapshot crosscheck, bool wait)
{
	HTSU_Result result;
	TransactionId xid = GetCurrentTransactionId();
	ItemId		lp;
	HeapTupleData oldtup;
	HeapTuple	heaptup;
	PageHeader	dp;
	Buffer		buffer,
				newbuf;
	bool		need_toast,
				already_marked;
	Size		newtupsize,
				pagefree;
	bool		have_tuple_lock = false;

	Assert(ItemPointerIsValid(otid));

	buffer = ReadBuffer(relation, ItemPointerGetBlockNumber(otid));
	LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);

	dp = (PageHeader) BufferGetPage(buffer);
	lp = PageGetItemId(dp, ItemPointerGetOffsetNumber(otid));

	oldtup.t_datamcxt = NULL;
	oldtup.t_data = (HeapTupleHeader) PageGetItem(dp, lp);
	oldtup.t_len = ItemIdGetLength(lp);
	oldtup.t_self = *otid;

	/*
	 * Note: beyond this point, use oldtup not otid to refer to old tuple.
	 * otid may very well point at newtup->t_self, which we will overwrite
	 * with the new tuple's location, so there's great risk of confusion if we
	 * use otid anymore.
	 */

l2:
	result = HeapTupleSatisfiesUpdate(oldtup.t_data, cid, buffer);

	if (result == HeapTupleInvisible)
	{
		LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
		ReleaseBuffer(buffer);
		elog(ERROR, "attempted to update invisible tuple");
	}
	else if (result == HeapTupleBeingUpdated && wait)
	{
		TransactionId xwait;
		uint16		infomask;

		/* must copy state data before unlocking buffer */
		xwait = HeapTupleHeaderGetXmax(oldtup.t_data);
		infomask = oldtup.t_data->t_infomask;

		LockBuffer(buffer, BUFFER_LOCK_UNLOCK);

		/*
		 * Acquire tuple lock to establish our priority for the tuple (see
		 * heap_lock_tuple).  LockTuple will release us when we are
		 * next-in-line for the tuple.
		 *
		 * If we are forced to "start over" below, we keep the tuple lock;
		 * this arranges that we stay at the head of the line while rechecking
		 * tuple state.
		 */
		if (!have_tuple_lock)
		{
			LockTuple(relation, &(oldtup.t_self), ExclusiveLock);
			have_tuple_lock = true;
		}

		/*
		 * Sleep until concurrent transaction ends.  Note that we don't care
		 * if the locker has an exclusive or shared lock, because we need
		 * exclusive.
		 */

		if (infomask & HEAP_XMAX_IS_MULTI)
		{
			/* wait for multixact */
			MultiXactIdWait((MultiXactId) xwait);
			LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);

			/*
			 * If xwait had just locked the tuple then some other xact could
			 * update this tuple before we get to this point.  Check for xmax
			 * change, and start over if so.
			 */
			if (!(oldtup.t_data->t_infomask & HEAP_XMAX_IS_MULTI) ||
				!TransactionIdEquals(HeapTupleHeaderGetXmax(oldtup.t_data),
									 xwait))
				goto l2;

			/*
			 * You might think the multixact is necessarily done here, but not
			 * so: it could have surviving members, namely our own xact or
			 * other subxacts of this backend.	It is legal for us to update
			 * the tuple in either case, however (the latter case is
			 * essentially a situation of upgrading our former shared lock to
			 * exclusive).	We don't bother changing the on-disk hint bits
			 * since we are about to overwrite the xmax altogether.
			 */
		}
		else
		{
			/* wait for regular transaction to end */
			XactLockTableWait(xwait);
			LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);

			/*
			 * xwait is done, but if xwait had just locked the tuple then some
			 * other xact could update this tuple before we get to this point.
			 * Check for xmax change, and start over if so.
			 */
			if ((oldtup.t_data->t_infomask & HEAP_XMAX_IS_MULTI) ||
				!TransactionIdEquals(HeapTupleHeaderGetXmax(oldtup.t_data),
									 xwait))
				goto l2;

			/* Otherwise we can mark it committed or aborted */
			if (!(oldtup.t_data->t_infomask & (HEAP_XMAX_COMMITTED |
											   HEAP_XMAX_INVALID)))
			{
				if (TransactionIdDidCommit(xwait))
					oldtup.t_data->t_infomask |= HEAP_XMAX_COMMITTED;
				else
					oldtup.t_data->t_infomask |= HEAP_XMAX_INVALID;
				SetBufferCommitInfoNeedsSave(buffer);
			}
		}

		/*
		 * We may overwrite if previous xmax aborted, or if it committed but
		 * only locked the tuple without updating it.
		 */
		if (oldtup.t_data->t_infomask & (HEAP_XMAX_INVALID |
										 HEAP_IS_LOCKED))
			result = HeapTupleMayBeUpdated;
		else
			result = HeapTupleUpdated;
	}

	if (crosscheck != InvalidSnapshot && result == HeapTupleMayBeUpdated)
	{
		/* Perform additional check for serializable RI updates */
		if (!HeapTupleSatisfiesSnapshot(oldtup.t_data, crosscheck, buffer))
			result = HeapTupleUpdated;
	}

	if (result != HeapTupleMayBeUpdated)
	{
		Assert(result == HeapTupleSelfUpdated ||
			   result == HeapTupleUpdated ||
			   result == HeapTupleBeingUpdated);
		Assert(!(oldtup.t_data->t_infomask & HEAP_XMAX_INVALID));
		*ctid = oldtup.t_data->t_ctid;
		*update_xmax = HeapTupleHeaderGetXmax(oldtup.t_data);
		LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
		ReleaseBuffer(buffer);
		if (have_tuple_lock)
			UnlockTuple(relation, &(oldtup.t_self), ExclusiveLock);
		return result;
	}

	/* Fill in OID and transaction status data for newtup */
	if (relation->rd_rel->relhasoids)
	{
#ifdef NOT_USED
		/* this is redundant with an Assert in HeapTupleSetOid */
		Assert(newtup->t_data->t_infomask & HEAP_HASOID);
#endif
		HeapTupleSetOid(newtup, HeapTupleGetOid(&oldtup));
	}
	else
	{
		/* check there is not space for an OID */
		Assert(!(newtup->t_data->t_infomask & HEAP_HASOID));
	}

	newtup->t_data->t_infomask &= ~(HEAP_XACT_MASK);
	newtup->t_data->t_infomask |= (HEAP_XMAX_INVALID | HEAP_UPDATED);
	HeapTupleHeaderSetXmin(newtup->t_data, xid);
	HeapTupleHeaderSetCmin(newtup->t_data, cid);
	HeapTupleHeaderSetXmax(newtup->t_data, 0);	/* zero out Datum fields */
	HeapTupleHeaderSetCmax(newtup->t_data, 0);	/* for cleanliness */

	/*
	 * If the toaster needs to be activated, OR if the new tuple will not fit
	 * on the same page as the old, then we need to release the context lock
	 * (but not the pin!) on the old tuple's buffer while we are off doing
	 * TOAST and/or table-file-extension work.	We must mark the old tuple to
	 * show that it's already being updated, else other processes may try to
	 * update it themselves.
	 *
	 * We need to invoke the toaster if there are already any out-of-line
	 * toasted values present, or if the new tuple is over-threshold.
	 */
	newtupsize = MAXALIGN(newtup->t_len);

	need_toast = (HeapTupleHasExternal(&oldtup) ||
				  HeapTupleHasExternal(newtup) ||
				  newtupsize > TOAST_TUPLE_THRESHOLD);

	pagefree = PageGetFreeSpace((Page) dp);

	if (need_toast || newtupsize > pagefree)
	{
		oldtup.t_data->t_infomask &= ~(HEAP_XMAX_COMMITTED |
									   HEAP_XMAX_INVALID |
									   HEAP_XMAX_IS_MULTI |