multixact.c

postgresql8.3.4源码,开源数据库

		slotno = SimpleLruReadPage(MultiXactMemberCtl, pageno, true, offset);
		xidptr = (TransactionId *) MultiXactMemberCtl->shared->page_buffer[slotno];
		xidptr += entryno;

		MemSet(xidptr, 0, BLCKSZ - (entryno * sizeof(TransactionId)));

		MultiXactMemberCtl->shared->page_dirty[slotno] = true;
	}

	LWLockRelease(MultiXactMemberControlLock);

	/*
	 * Initialize lastTruncationPoint to invalid, ensuring that the first
	 * checkpoint will try to do truncation.
	 */
	MultiXactState->lastTruncationPoint = InvalidMultiXactId;
}

/*
 * This must be called ONCE during postmaster or standalone-backend shutdown
 */
void
ShutdownMultiXact(void)
{
	/* Flush dirty MultiXact pages to disk */
	SimpleLruFlush(MultiXactOffsetCtl, false);
	SimpleLruFlush(MultiXactMemberCtl, false);
}

/*
 * Get the next MultiXactId and offset to save in a checkpoint record
 */
void
MultiXactGetCheckptMulti(bool is_shutdown,
						 MultiXactId *nextMulti,
						 MultiXactOffset *nextMultiOffset)
{
	LWLockAcquire(MultiXactGenLock, LW_SHARED);

	*nextMulti = MultiXactState->nextMXact;
	*nextMultiOffset = MultiXactState->nextOffset;

	LWLockRelease(MultiXactGenLock);

	debug_elog4(DEBUG2, "MultiXact: checkpoint is nextMulti %u, nextOffset %u",
				*nextMulti, *nextMultiOffset);
}

/*
 * Perform a checkpoint --- either during shutdown, or on-the-fly
 */
void
CheckPointMultiXact(void)
{
	/* Flush dirty MultiXact pages to disk */
	SimpleLruFlush(MultiXactOffsetCtl, true);
	SimpleLruFlush(MultiXactMemberCtl, true);

	/*
	 * Truncate the SLRU files.  This could be done at any time, but
	 * checkpoint seems a reasonable place for it.	There is one exception: if
	 * we are called during xlog recovery, then shared->latest_page_number
	 * isn't valid (because StartupMultiXact hasn't been called yet) and so
	 * SimpleLruTruncate would get confused.  It seems best not to risk
	 * removing any data during recovery anyway, so don't truncate.
	 */
	if (!InRecovery)
		TruncateMultiXact();
}

/*
 * Set the next-to-be-assigned MultiXactId and offset
 *
 * This is used when we can determine the correct next ID/offset exactly
 * from a checkpoint record.  We need no locking since it is only called
 * during bootstrap and XLog replay.
 */
void
MultiXactSetNextMXact(MultiXactId nextMulti,
					  MultiXactOffset nextMultiOffset)
{
	debug_elog4(DEBUG2, "MultiXact: setting next multi to %u offset %u",
				nextMulti, nextMultiOffset);
	MultiXactState->nextMXact = nextMulti;
	MultiXactState->nextOffset = nextMultiOffset;
}

/*
 * Ensure the next-to-be-assigned MultiXactId is at least minMulti,
 * and similarly nextOffset is at least minMultiOffset
 *
 * This is used when we can determine minimum safe values from an XLog
 * record (either an on-line checkpoint or an mxact creation log entry).
 * We need no locking since it is only called during XLog replay.
 */
void
MultiXactAdvanceNextMXact(MultiXactId minMulti,
						  MultiXactOffset minMultiOffset)
{
	if (MultiXactIdPrecedes(MultiXactState->nextMXact, minMulti))
	{
		debug_elog3(DEBUG2, "MultiXact: setting next multi to %u", minMulti);
		MultiXactState->nextMXact = minMulti;
	}
	if (MultiXactOffsetPrecedes(MultiXactState->nextOffset, minMultiOffset))
	{
		debug_elog3(DEBUG2, "MultiXact: setting next offset to %u",
					minMultiOffset);
		MultiXactState->nextOffset = minMultiOffset;
	}
}

/*
 * Make sure that MultiXactOffset has room for a newly-allocated MultiXactId.
 *
 * NB: this is called while holding MultiXactGenLock.  We want it to be very
 * fast most of the time; even when it's not so fast, no actual I/O need
 * happen unless we're forced to write out a dirty log or xlog page to make
 * room in shared memory.
 */
static void
ExtendMultiXactOffset(MultiXactId multi)
{
	int			pageno;

	/*
	 * No work except at first MultiXactId of a page.  But beware: just after
	 * wraparound, the first MultiXactId of page zero is FirstMultiXactId.
	 */
	if (MultiXactIdToOffsetEntry(multi) != 0 &&
		multi != FirstMultiXactId)
		return;

	pageno = MultiXactIdToOffsetPage(multi);

	LWLockAcquire(MultiXactOffsetControlLock, LW_EXCLUSIVE);

	/* Zero the page and make an XLOG entry about it */
	ZeroMultiXactOffsetPage(pageno, true);

	LWLockRelease(MultiXactOffsetControlLock);
}

/*
 * Make sure that MultiXactMember has room for the members of a newly-
 * allocated MultiXactId.
 *
 * Like the above routine, this is called while holding MultiXactGenLock;
 * same comments apply.
 */
static void
ExtendMultiXactMember(MultiXactOffset offset, int nmembers)
{
	/*
	 * It's possible that the members span more than one page of the members
	 * file, so we loop to ensure we consider each page.  The coding is not
	 * optimal if the members span several pages, but that seems unusual
	 * enough to not worry much about.
	 */
	while (nmembers > 0)
	{
		int			entryno;

		/*
		 * Only zero when at first entry of a page.
		 */
		entryno = MXOffsetToMemberEntry(offset);
		if (entryno == 0)
		{
			int			pageno;

			pageno = MXOffsetToMemberPage(offset);

			LWLockAcquire(MultiXactMemberControlLock, LW_EXCLUSIVE);

			/* Zero the page and make an XLOG entry about it */
			ZeroMultiXactMemberPage(pageno, true);

			LWLockRelease(MultiXactMemberControlLock);
		}

		/* Advance to next page (OK if nmembers goes negative) */
		offset += (MULTIXACT_MEMBERS_PER_PAGE - entryno);
		nmembers -= (MULTIXACT_MEMBERS_PER_PAGE - entryno);
	}
}

/*
 * Remove all MultiXactOffset and MultiXactMember segments before the oldest
 * ones still of interest.
 *
 * This is called only during checkpoints.	We assume no more than one
 * backend does this at a time.
 *
 * XXX do we have any issues with needing to checkpoint here?
 */
static void
TruncateMultiXact(void)
{
	MultiXactId nextMXact;
	MultiXactOffset nextOffset;
	MultiXactId oldestMXact;
	MultiXactOffset oldestOffset;
	int			cutoffPage;
	int			i;

	/*
	 * First, compute where we can safely truncate.  Per notes above, this is
	 * the oldest valid value among all the OldestMemberMXactId[] and
	 * OldestVisibleMXactId[] entries, or nextMXact if none are valid.
	 */
	LWLockAcquire(MultiXactGenLock, LW_SHARED);

	/*
	 * We have to beware of the possibility that nextMXact is in the
	 * wrapped-around state.  We don't fix the counter itself here, but we
	 * must be sure to use a valid value in our calculation.
	 */
	nextMXact = MultiXactState->nextMXact;
	if (nextMXact < FirstMultiXactId)
		nextMXact = FirstMultiXactId;

	oldestMXact = nextMXact;
	for (i = 1; i <= MaxBackends; i++)
	{
		MultiXactId thisoldest;

		thisoldest = OldestMemberMXactId[i];
		if (MultiXactIdIsValid(thisoldest) &&
			MultiXactIdPrecedes(thisoldest, oldestMXact))
			oldestMXact = thisoldest;
		thisoldest = OldestVisibleMXactId[i];
		if (MultiXactIdIsValid(thisoldest) &&
			MultiXactIdPrecedes(thisoldest, oldestMXact))
			oldestMXact = thisoldest;
	}

	/* Save the current nextOffset too */
	nextOffset = MultiXactState->nextOffset;

	LWLockRelease(MultiXactGenLock);

	debug_elog3(DEBUG2, "MultiXact: truncation point = %u", oldestMXact);

	/*
	 * If we already truncated at this point, do nothing.  This saves time
	 * when no MultiXacts are getting used, which is probably not uncommon.
	 */
	if (MultiXactState->lastTruncationPoint == oldestMXact)
		return;

	/*
	 * We need to determine where to truncate MultiXactMember.	If we found a
	 * valid oldest MultiXactId, read its starting offset; otherwise we use
	 * the nextOffset value we saved above.
	 */
	if (oldestMXact == nextMXact)
		oldestOffset = nextOffset;
	else
	{
		int			pageno;
		int			slotno;
		int			entryno;
		MultiXactOffset *offptr;

		/* lock is acquired by SimpleLruReadPage_ReadOnly */

		pageno = MultiXactIdToOffsetPage(oldestMXact);
		entryno = MultiXactIdToOffsetEntry(oldestMXact);

		slotno = SimpleLruReadPage_ReadOnly(MultiXactOffsetCtl, pageno, oldestMXact);
		offptr = (MultiXactOffset *) MultiXactOffsetCtl->shared->page_buffer[slotno];
		offptr += entryno;
		oldestOffset = *offptr;

		LWLockRelease(MultiXactOffsetControlLock);
	}

	/*
	 * The cutoff point is the start of the segment containing oldestMXact. We
	 * pass the *page* containing oldestMXact to SimpleLruTruncate.
	 */
	cutoffPage = MultiXactIdToOffsetPage(oldestMXact);

	SimpleLruTruncate(MultiXactOffsetCtl, cutoffPage);

	/*
	 * Also truncate MultiXactMember at the previously determined offset.
	 */
	cutoffPage = MXOffsetToMemberPage(oldestOffset);

	SimpleLruTruncate(MultiXactMemberCtl, cutoffPage);

	/*
	 * Set the last known truncation point.  We don't need a lock for this
	 * since only one backend does checkpoints at a time.
	 */
	MultiXactState->lastTruncationPoint = oldestMXact;
}

/*
 * Decide which of two MultiXactOffset page numbers is "older" for truncation
 * purposes.
 *
 * We need to use comparison of MultiXactId here in order to do the right
 * thing with wraparound.  However, if we are asked about page number zero, we
 * don't want to hand InvalidMultiXactId to MultiXactIdPrecedes: it'll get
 * weird.  So, offset both multis by FirstMultiXactId to avoid that.
 * (Actually, the current implementation doesn't do anything weird with
 * InvalidMultiXactId, but there's no harm in leaving this code like this.)
 */
static bool
MultiXactOffsetPagePrecedes(int page1, int page2)
{
	MultiXactId multi1;
	MultiXactId multi2;

	multi1 = ((MultiXactId) page1) * MULTIXACT_OFFSETS_PER_PAGE;
	multi1 += FirstMultiXactId;
	multi2 = ((MultiXactId) page2) * MULTIXACT_OFFSETS_PER_PAGE;
	multi2 += FirstMultiXactId;

	return MultiXactIdPrecedes(multi1, multi2);
}

/*
 * Decide which of two MultiXactMember page numbers is "older" for truncation
 * purposes.  There is no "invalid offset number" so use the numbers verbatim.
 */
static bool
MultiXactMemberPagePrecedes(int page1, int page2)
{
	MultiXactOffset offset1;
	MultiXactOffset offset2;

	offset1 = ((MultiXactOffset) page1) * MULTIXACT_MEMBERS_PER_PAGE;
	offset2 = ((MultiXactOffset) page2) * MULTIXACT_MEMBERS_PER_PAGE;

	return MultiXactOffsetPrecedes(offset1, offset2);
}

/*
 * Decide which of two MultiXactIds is earlier.
 *
 * XXX do we need to do something special for InvalidMultiXactId?
 * (Doesn't look like it.)
 */
static bool
MultiXactIdPrecedes(MultiXactId multi1, MultiXactId multi2)
{
	int32		diff = (int32) (multi1 - multi2);

	return (diff < 0);
}

/*
 * Decide which of two offsets is earlier.
 */
static bool
MultiXactOffsetPrecedes(MultiXactOffset offset1, MultiXactOffset offset2)
{
	int32		diff = (int32) (offset1 - offset2);

	return (diff < 0);
}


/*
 * Write an xlog record reflecting the zeroing of either a MEMBERs or
 * OFFSETs page (info shows which)
 */
static void
WriteMZeroPageXlogRec(int pageno, uint8 info)
{
	XLogRecData rdata;

	rdata.data = (char *) (&pageno);
	rdata.len = sizeof(int);
	rdata.buffer = InvalidBuffer;
	rdata.next = NULL;
	(void) XLogInsert(RM_MULTIXACT_ID, info, &rdata);
}

/*
 * MULTIXACT resource manager's routines
 */
void
multixact_redo(XLogRecPtr lsn, XLogRecord *record)
{
	uint8		info = record->xl_info & ~XLR_INFO_MASK;

	if (info == XLOG_MULTIXACT_ZERO_OFF_PAGE)
	{
		int			pageno;
		int			slotno;

		memcpy(&pageno, XLogRecGetData(record), sizeof(int));

		LWLockAcquire(MultiXactOffsetControlLock, LW_EXCLUSIVE);

		slotno = ZeroMultiXactOffsetPage(pageno, false);
		SimpleLruWritePage(MultiXactOffsetCtl, slotno, NULL);
		Assert(!MultiXactOffsetCtl->shared->page_dirty[slotno]);

		LWLockRelease(MultiXactOffsetControlLock);
	}
	else if (info == XLOG_MULTIXACT_ZERO_MEM_PAGE)
	{
		int			pageno;
		int			slotno;

		memcpy(&pageno, XLogRecGetData(record), sizeof(int));

		LWLockAcquire(MultiXactMemberControlLock, LW_EXCLUSIVE);

		slotno = ZeroMultiXactMemberPage(pageno, false);
		SimpleLruWritePage(MultiXactMemberCtl, slotno, NULL);
		Assert(!MultiXactMemberCtl->shared->page_dirty[slotno]);

		LWLockRelease(MultiXactMemberControlLock);
	}
	else if (info == XLOG_MULTIXACT_CREATE_ID)
	{
		xl_multixact_create *xlrec = (xl_multixact_create *) XLogRecGetData(record);
		TransactionId *xids = xlrec->xids;
		TransactionId max_xid;
		int			i;

		/* Store the data back into the SLRU files */
		RecordNewMultiXact(xlrec->mid, xlrec->moff, xlrec->nxids, xids);

		/* Make sure nextMXact/nextOffset are beyond what this record has */
		MultiXactAdvanceNextMXact(xlrec->mid + 1, xlrec->moff + xlrec->nxids);

		/*
		 * Make sure nextXid is beyond any XID mentioned in the record. This
		 * should be unnecessary, since any XID found here ought to have other
		 * evidence in the XLOG, but let's be safe.
		 */
		max_xid = record->xl_xid;
		for (i = 0; i < xlrec->nxids; i++)
		{
			if (TransactionIdPrecedes(max_xid, xids[i]))
				max_xid = xids[i];
		}
		if (TransactionIdFollowsOrEquals(max_xid,
										 ShmemVariableCache->nextXid))
		{
			ShmemVariableCache->nextXid = max_xid;
			TransactionIdAdvance(ShmemVariableCache->nextXid);
		}
	}
	else
		elog(PANIC, "multixact_redo: unknown op code %u", info);
}

void
multixact_desc(StringInfo buf, uint8 xl_info, char *rec)
{
	uint8		info = xl_info & ~XLR_INFO_MASK;

	if (info == XLOG_MULTIXACT_ZERO_OFF_PAGE)
	{
		int			pageno;

		memcpy(&pageno, rec, sizeof(int));
		appendStringInfo(buf, "zero offsets page: %d", pageno);
	}
	else if (info == XLOG_MULTIXACT_ZERO_MEM_PAGE)
	{
		int			pageno;

		memcpy(&pageno, rec, sizeof(int));
		appendStringInfo(buf, "zero members page: %d", pageno);
	}
	else if (info == XLOG_MULTIXACT_CREATE_ID)
	{
		xl_multixact_create *xlrec = (xl_multixact_create *) rec;
		int			i;

		appendStringInfo(buf, "create multixact %u offset %u:",
						 xlrec->mid, xlrec->moff);
		for (i = 0; i < xlrec->nxids; i++)
			appendStringInfo(buf, " %u", xlrec->xids[i]);
	}
	else
		appendStringInfo(buf, "UNKNOWN");
}