multixact.c

postgresql8.3.4源码,开源数据库

/*-------------------------------------------------------------------------
 *
 * multixact.c
 *		PostgreSQL multi-transaction-log manager
 *
 * The pg_multixact manager is a pg_clog-like manager that stores an array
 * of TransactionIds for each MultiXactId.	It is a fundamental part of the
 * shared-row-lock implementation.	A share-locked tuple stores a
 * MultiXactId in its Xmax, and a transaction that needs to wait for the
 * tuple to be unlocked can sleep on the potentially-several TransactionIds
 * that compose the MultiXactId.
 *
 * We use two SLRU areas, one for storing the offsets at which the data
 * starts for each MultiXactId in the other one.  This trick allows us to
 * store variable length arrays of TransactionIds.	(We could alternatively
 * use one area containing counts and TransactionIds, with valid MultiXactId
 * values pointing at slots containing counts; but that way seems less robust
 * since it would get completely confused if someone inquired about a bogus
 * MultiXactId that pointed to an intermediate slot containing an XID.)
 *
 * XLOG interactions: this module generates an XLOG record whenever a new
 * OFFSETs or MEMBERs page is initialized to zeroes, as well as an XLOG record
 * whenever a new MultiXactId is defined.  This allows us to completely
 * rebuild the data entered since the last checkpoint during XLOG replay.
 * Because this is possible, we need not follow the normal rule of
 * "write WAL before data"; the only correctness guarantee needed is that
 * we flush and sync all dirty OFFSETs and MEMBERs pages to disk before a
 * checkpoint is considered complete.  If a page does make it to disk ahead
 * of corresponding WAL records, it will be forcibly zeroed before use anyway.
 * Therefore, we don't need to mark our pages with LSN information; we have
 * enough synchronization already.
 *
 * Like clog.c, and unlike subtrans.c, we have to preserve state across
 * crashes and ensure that MXID and offset numbering increases monotonically
 * across a crash.	We do this in the same way as it's done for transaction
 * IDs: the WAL record is guaranteed to contain evidence of every MXID we
 * could need to worry about, and we just make sure that at the end of
 * replay, the next-MXID and next-offset counters are at least as large as
 * anything we saw during replay.
 *
 *
 * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * $PostgreSQL: pgsql/src/backend/access/transam/multixact.c,v 1.27 2008/01/01 19:45:46 momjian Exp $
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include "access/multixact.h"
#include "access/slru.h"
#include "access/transam.h"
#include "access/xact.h"
#include "miscadmin.h"
#include "storage/backendid.h"
#include "storage/lmgr.h"
#include "utils/memutils.h"
#include "storage/procarray.h"


/*
 * Defines for MultiXactOffset page sizes.	A page is the same BLCKSZ as is
 * used everywhere else in Postgres.
 *
 * Note: because both MultiXactOffsets and TransactionIds are 32 bits and
 * wrap around at 0xFFFFFFFF, MultiXact page numbering also wraps around at
 * 0xFFFFFFFF/MULTIXACT_*_PER_PAGE, and segment numbering at
 * 0xFFFFFFFF/MULTIXACT_*_PER_PAGE/SLRU_SEGMENTS_PER_PAGE.	We need take no
 * explicit notice of that fact in this module, except when comparing segment
 * and page numbers in TruncateMultiXact
 * (see MultiXact{Offset,Member}PagePrecedes).
 */

/* We need four bytes per offset and also four bytes per member */
#define MULTIXACT_OFFSETS_PER_PAGE (BLCKSZ / sizeof(MultiXactOffset))
#define MULTIXACT_MEMBERS_PER_PAGE (BLCKSZ / sizeof(TransactionId))

#define MultiXactIdToOffsetPage(xid) \
	((xid) / (MultiXactOffset) MULTIXACT_OFFSETS_PER_PAGE)
#define MultiXactIdToOffsetEntry(xid) \
	((xid) % (MultiXactOffset) MULTIXACT_OFFSETS_PER_PAGE)

#define MXOffsetToMemberPage(xid) \
	((xid) / (TransactionId) MULTIXACT_MEMBERS_PER_PAGE)
#define MXOffsetToMemberEntry(xid) \
	((xid) % (TransactionId) MULTIXACT_MEMBERS_PER_PAGE)


/*
 * Links to shared-memory data structures for MultiXact control
 */
static SlruCtlData MultiXactOffsetCtlData;
static SlruCtlData MultiXactMemberCtlData;

#define MultiXactOffsetCtl	(&MultiXactOffsetCtlData)
#define MultiXactMemberCtl	(&MultiXactMemberCtlData)

/*
 * MultiXact state shared across all backends.	All this state is protected
 * by MultiXactGenLock.  (We also use MultiXactOffsetControlLock and
 * MultiXactMemberControlLock to guard accesses to the two sets of SLRU
 * buffers.  For concurrency's sake, we avoid holding more than one of these
 * locks at a time.)
 */
typedef struct MultiXactStateData
{
	/* next-to-be-assigned MultiXactId */
	MultiXactId nextMXact;

	/* next-to-be-assigned offset */
	MultiXactOffset nextOffset;

	/* the Offset SLRU area was last truncated at this MultiXactId */
	MultiXactId lastTruncationPoint;

	/*
	 * Per-backend data starts here.  We have two arrays stored in the area
	 * immediately following the MultiXactStateData struct. Each is indexed by
	 * BackendId.  (Note: valid BackendIds run from 1 to MaxBackends; element
	 * zero of each array is never used.)
	 *
	 * OldestMemberMXactId[k] is the oldest MultiXactId each backend's current
	 * transaction(s) could possibly be a member of, or InvalidMultiXactId
	 * when the backend has no live transaction that could possibly be a
	 * member of a MultiXact.  Each backend sets its entry to the current
	 * nextMXact counter just before first acquiring a shared lock in a given
	 * transaction, and clears it at transaction end. (This works because only
	 * during or after acquiring a shared lock could an XID possibly become a
	 * member of a MultiXact, and that MultiXact would have to be created
	 * during or after the lock acquisition.)
	 *
	 * OldestVisibleMXactId[k] is the oldest MultiXactId each backend's
	 * current transaction(s) think is potentially live, or InvalidMultiXactId
	 * when not in a transaction or not in a transaction that's paid any
	 * attention to MultiXacts yet.  This is computed when first needed in a
	 * given transaction, and cleared at transaction end.  We can compute it
	 * as the minimum of the valid OldestMemberMXactId[] entries at the time
	 * we compute it (using nextMXact if none are valid).  Each backend is
	 * required not to attempt to access any SLRU data for MultiXactIds older
	 * than its own OldestVisibleMXactId[] setting; this is necessary because
	 * the checkpointer could truncate away such data at any instant.
	 *
	 * The checkpointer can compute the safe truncation point as the oldest
	 * valid value among all the OldestMemberMXactId[] and
	 * OldestVisibleMXactId[] entries, or nextMXact if none are valid.
	 * Clearly, it is not possible for any later-computed OldestVisibleMXactId
	 * value to be older than this, and so there is no risk of truncating data
	 * that is still needed.
	 */
	MultiXactId perBackendXactIds[1];	/* VARIABLE LENGTH ARRAY */
} MultiXactStateData;

/* Pointers to the state data in shared memory */
static MultiXactStateData *MultiXactState;
static MultiXactId *OldestMemberMXactId;
static MultiXactId *OldestVisibleMXactId;


/*
 * Definitions for the backend-local MultiXactId cache.
 *
 * We use this cache to store known MultiXacts, so we don't need to go to
 * SLRU areas everytime.
 *
 * The cache lasts for the duration of a single transaction, the rationale
 * for this being that most entries will contain our own TransactionId and
 * so they will be uninteresting by the time our next transaction starts.
 * (XXX not clear that this is correct --- other members of the MultiXact
 * could hang around longer than we did.  However, it's not clear what a
 * better policy for flushing old cache entries would be.)
 *
 * We allocate the cache entries in a memory context that is deleted at
 * transaction end, so we don't need to do retail freeing of entries.
 */
typedef struct mXactCacheEnt
{
	struct mXactCacheEnt *next;
	MultiXactId multi;
	int			nxids;
	TransactionId xids[1];		/* VARIABLE LENGTH ARRAY */
} mXactCacheEnt;

static mXactCacheEnt *MXactCache = NULL;
static MemoryContext MXactContext = NULL;


#ifdef MULTIXACT_DEBUG
#define debug_elog2(a,b) elog(a,b)
#define debug_elog3(a,b,c) elog(a,b,c)
#define debug_elog4(a,b,c,d) elog(a,b,c,d)
#define debug_elog5(a,b,c,d,e) elog(a,b,c,d,e)
#else
#define debug_elog2(a,b)
#define debug_elog3(a,b,c)
#define debug_elog4(a,b,c,d)
#define debug_elog5(a,b,c,d,e)
#endif

/* internal MultiXactId management */
static void MultiXactIdSetOldestVisible(void);
static MultiXactId CreateMultiXactId(int nxids, TransactionId *xids);
static void RecordNewMultiXact(MultiXactId multi, MultiXactOffset offset,
				   int nxids, TransactionId *xids);
static MultiXactId GetNewMultiXactId(int nxids, MultiXactOffset *offset);

/* MultiXact cache management */
static MultiXactId mXactCacheGetBySet(int nxids, TransactionId *xids);
static int	mXactCacheGetById(MultiXactId multi, TransactionId **xids);
static void mXactCachePut(MultiXactId multi, int nxids, TransactionId *xids);
static int	xidComparator(const void *arg1, const void *arg2);

#ifdef MULTIXACT_DEBUG
static char *mxid_to_string(MultiXactId multi, int nxids, TransactionId *xids);
#endif

/* management of SLRU infrastructure */
static int	ZeroMultiXactOffsetPage(int pageno, bool writeXlog);
static int	ZeroMultiXactMemberPage(int pageno, bool writeXlog);
static bool MultiXactOffsetPagePrecedes(int page1, int page2);
static bool MultiXactMemberPagePrecedes(int page1, int page2);
static bool MultiXactIdPrecedes(MultiXactId multi1, MultiXactId multi2);
static bool MultiXactOffsetPrecedes(MultiXactOffset offset1,
						MultiXactOffset offset2);
static void ExtendMultiXactOffset(MultiXactId multi);
static void ExtendMultiXactMember(MultiXactOffset offset, int nmembers);
static void TruncateMultiXact(void);
static void WriteMZeroPageXlogRec(int pageno, uint8 info);


/*
 * MultiXactIdCreate
 *		Construct a MultiXactId representing two TransactionIds.
 *
 * The two XIDs must be different.
 *
 * NB - we don't worry about our local MultiXactId cache here, because that
 * is handled by the lower-level routines.
 */
MultiXactId
MultiXactIdCreate(TransactionId xid1, TransactionId xid2)
{
	MultiXactId newMulti;
	TransactionId xids[2];

	AssertArg(TransactionIdIsValid(xid1));
	AssertArg(TransactionIdIsValid(xid2));

	Assert(!TransactionIdEquals(xid1, xid2));

	/*
	 * Note: unlike MultiXactIdExpand, we don't bother to check that both XIDs
	 * are still running.  In typical usage, xid2 will be our own XID and the
	 * caller just did a check on xid1, so it'd be wasted effort.
	 */

	xids[0] = xid1;
	xids[1] = xid2;

	newMulti = CreateMultiXactId(2, xids);

	debug_elog5(DEBUG2, "Create: returning %u for %u, %u",
				newMulti, xid1, xid2);

	return newMulti;
}

/*
 * MultiXactIdExpand
 *		Add a TransactionId to a pre-existing MultiXactId.
 *
 * If the TransactionId is already a member of the passed MultiXactId,
 * just return it as-is.
 *
 * Note that we do NOT actually modify the membership of a pre-existing
 * MultiXactId; instead we create a new one.  This is necessary to avoid
 * a race condition against MultiXactIdWait (see notes there).
 *
 * NB - we don't worry about our local MultiXactId cache here, because that
 * is handled by the lower-level routines.
 */
MultiXactId
MultiXactIdExpand(MultiXactId multi, TransactionId xid)
{
	MultiXactId newMulti;
	TransactionId *members;
	TransactionId *newMembers;
	int			nmembers;
	int			i;
	int			j;

	AssertArg(MultiXactIdIsValid(multi));
	AssertArg(TransactionIdIsValid(xid));

	debug_elog4(DEBUG2, "Expand: received multi %u, xid %u",
				multi, xid);

	nmembers = GetMultiXactIdMembers(multi, &members);

	if (nmembers < 0)
	{
		/*
		 * The MultiXactId is obsolete.  This can only happen if all the
		 * MultiXactId members stop running between the caller checking and
		 * passing it to us.  It would be better to return that fact to the
		 * caller, but it would complicate the API and it's unlikely to happen
		 * too often, so just deal with it by creating a singleton MultiXact.
		 */
		newMulti = CreateMultiXactId(1, &xid);

		debug_elog4(DEBUG2, "Expand: %u has no members, create singleton %u",
					multi, newMulti);
		return newMulti;
	}

	/*
	 * If the TransactionId is already a member of the MultiXactId, just
	 * return the existing MultiXactId.
	 */
	for (i = 0; i < nmembers; i++)
	{
		if (TransactionIdEquals(members[i], xid))
		{
			debug_elog4(DEBUG2, "Expand: %u is already a member of %u",
						xid, multi);
			pfree(members);
			return multi;
		}
	}

	/*
	 * Determine which of the members of the MultiXactId are still running,
	 * and use them to create a new one.  (Removing dead members is just an
	 * optimization, but a useful one.	Note we have the same race condition
	 * here as above: j could be 0 at the end of the loop.)
	 */
	newMembers = (TransactionId *)
		palloc(sizeof(TransactionId) * (nmembers + 1));

	for (i = 0, j = 0; i < nmembers; i++)
	{
		if (TransactionIdIsInProgress(members[i]))
			newMembers[j++] = members[i];
	}

	newMembers[j++] = xid;
	newMulti = CreateMultiXactId(j, newMembers);

	pfree(members);
	pfree(newMembers);

	debug_elog3(DEBUG2, "Expand: returning new multi %u", newMulti);

	return newMulti;
}

/*
 * MultiXactIdIsRunning
 *		Returns whether a MultiXactId is "running".
 *
 * We return true if at least one member of the given MultiXactId is still
 * running.  Note that a "false" result is certain not to change,
 * because it is not legal to add members to an existing MultiXactId.
 */
bool
MultiXactIdIsRunning(MultiXactId multi)
{
	TransactionId *members;
	int			nmembers;
	int			i;

	debug_elog3(DEBUG2, "IsRunning %u?", multi);

	nmembers = GetMultiXactIdMembers(multi, &members);

	if (nmembers < 0)
	{
		debug_elog2(DEBUG2, "IsRunning: no members");
		return false;
	}

	/*
	 * Checking for myself is cheap compared to looking in shared memory, so
	 * first do the equivalent of MultiXactIdIsCurrent().  This is not needed
	 * for correctness, it's just a fast path.
	 */
	for (i = 0; i < nmembers; i++)
	{
		if (TransactionIdIsCurrentTransactionId(members[i]))
		{
			debug_elog3(DEBUG2, "IsRunning: I (%d) am running!", i);
			pfree(members);
			return true;
		}
	}

	/*
	 * This could be made faster by having another entry point in procarray.c,
	 * walking the PGPROC array only once for all the members.	But in most
	 * cases nmembers should be small enough that it doesn't much matter.
	 */
	for (i = 0; i < nmembers; i++)
	{
		if (TransactionIdIsInProgress(members[i]))
		{
			debug_elog4(DEBUG2, "IsRunning: member %d (%u) is running",
						i, members[i]);
			pfree(members);
			return true;
		}
	}

	pfree(members);

	debug_elog3(DEBUG2, "IsRunning: %u is not running", multi);

	return false;
}

/*
 * MultiXactIdIsCurrent
 *		Returns true if the current transaction is a member of the MultiXactId.
 *
 * We return true if any live subtransaction of the current top-level
 * transaction is a member.  This is appropriate for the same reason that a
 * lock held by any such subtransaction is globally equivalent to a lock
 * held by the current subtransaction: no such lock could be released without
 * aborting this subtransaction, and hence releasing its locks.  So it's not
 * necessary to add the current subxact to the MultiXact separately.
 */
bool
MultiXactIdIsCurrent(MultiXactId multi)
{
	bool		result = false;
	TransactionId *members;
	int			nmembers;
	int			i;

	nmembers = GetMultiXactIdMembers(multi, &members);

	if (nmembers < 0)
		return false;

	for (i = 0; i < nmembers; i++)
	{
		if (TransactionIdIsCurrentTransactionId(members[i]))
		{
			result = true;
			break;
		}
	}

	pfree(members);

	return result;
}

/*
 * MultiXactIdSetOldestMember
 *		Save the oldest MultiXactId this transaction could be a member of.
 *
 * We set the OldestMemberMXactId for a given transaction the first time
 * it's going to acquire a shared lock.  We need to do this even if we end
 * up using a TransactionId instead of a MultiXactId, because there is a
 * chance that another transaction would add our XID to a MultiXactId.
 *
 * The value to set is the next-to-be-assigned MultiXactId, so this is meant
 * to be called just before acquiring a shared lock.
 */
void
MultiXactIdSetOldestMember(void)
{
	if (!MultiXactIdIsValid(OldestMemberMXactId[MyBackendId]))
	{
		MultiXactId nextMXact;

		/*
		 * You might think we don't need to acquire a lock here, since
		 * fetching and storing of TransactionIds is probably atomic, but in
		 * fact we do: suppose we pick up nextMXact and then lose the CPU for
		 * a long time.  Someone else could advance nextMXact, and then
		 * another someone else could compute an OldestVisibleMXactId that
		 * would be after the value we are going to store when we get control
		 * back.  Which would be wrong.
		 */
		LWLockAcquire(MultiXactGenLock, LW_EXCLUSIVE);

		/*
		 * 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 store a valid value in our array entry.