clog.c

postgresql8.3.4源码,开源数据库

/*-------------------------------------------------------------------------
 *
 * clog.c
 *		PostgreSQL transaction-commit-log manager
 *
 * This module replaces the old "pg_log" access code, which treated pg_log
 * essentially like a relation, in that it went through the regular buffer
 * manager.  The problem with that was that there wasn't any good way to
 * recycle storage space for transactions so old that they'll never be
 * looked up again.  Now we use specialized access code so that the commit
 * log can be broken into relatively small, independent segments.
 *
 * XLOG interactions: this module generates an XLOG record whenever a new
 * CLOG page is initialized to zeroes.	Other writes of CLOG come from
 * recording of transaction commit or abort in xact.c, which generates its
 * own XLOG records for these events and will re-perform the status update
 * on redo; so we need make no additional XLOG entry here.	For synchronous
 * transaction commits, the XLOG is guaranteed flushed through the XLOG commit
 * record before we are called to log a commit, so the WAL rule "write xlog
 * before data" is satisfied automatically.  However, for async commits we
 * must track the latest LSN affecting each CLOG page, so that we can flush
 * XLOG that far and satisfy the WAL rule.	We don't have to worry about this
 * for aborts (whether sync or async), since the post-crash assumption would
 * be that such transactions failed anyway.
 *
 * 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/clog.c,v 1.46 2008/01/01 19:45:46 momjian Exp $
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include "access/clog.h"
#include "access/slru.h"
#include "access/transam.h"
#include "postmaster/bgwriter.h"

/*
 * Defines for CLOG page sizes.  A page is the same BLCKSZ as is used
 * everywhere else in Postgres.
 *
 * Note: because TransactionIds are 32 bits and wrap around at 0xFFFFFFFF,
 * CLOG page numbering also wraps around at 0xFFFFFFFF/CLOG_XACTS_PER_PAGE,
 * and CLOG segment numbering at 0xFFFFFFFF/CLOG_XACTS_PER_SEGMENT.  We need
 * take no explicit notice of that fact in this module, except when comparing
 * segment and page numbers in TruncateCLOG (see CLOGPagePrecedes).
 */

/* We need two bits per xact, so four xacts fit in a byte */
#define CLOG_BITS_PER_XACT	2
#define CLOG_XACTS_PER_BYTE 4
#define CLOG_XACTS_PER_PAGE (BLCKSZ * CLOG_XACTS_PER_BYTE)
#define CLOG_XACT_BITMASK	((1 << CLOG_BITS_PER_XACT) - 1)

#define TransactionIdToPage(xid)	((xid) / (TransactionId) CLOG_XACTS_PER_PAGE)
#define TransactionIdToPgIndex(xid) ((xid) % (TransactionId) CLOG_XACTS_PER_PAGE)
#define TransactionIdToByte(xid)	(TransactionIdToPgIndex(xid) / CLOG_XACTS_PER_BYTE)
#define TransactionIdToBIndex(xid)	((xid) % (TransactionId) CLOG_XACTS_PER_BYTE)

/* We store the latest async LSN for each group of transactions */
#define CLOG_XACTS_PER_LSN_GROUP	32	/* keep this a power of 2 */
#define CLOG_LSNS_PER_PAGE	(CLOG_XACTS_PER_PAGE / CLOG_XACTS_PER_LSN_GROUP)

#define GetLSNIndex(slotno, xid)	((slotno) * CLOG_LSNS_PER_PAGE + \
	((xid) % (TransactionId) CLOG_XACTS_PER_PAGE) / CLOG_XACTS_PER_LSN_GROUP)


/*
 * Link to shared-memory data structures for CLOG control
 */
static SlruCtlData ClogCtlData;

#define ClogCtl (&ClogCtlData)


static int	ZeroCLOGPage(int pageno, bool writeXlog);
static bool CLOGPagePrecedes(int page1, int page2);
static void WriteZeroPageXlogRec(int pageno);
static void WriteTruncateXlogRec(int pageno);


/*
 * Record the final state of a transaction in the commit log.
 *
 * lsn must be the WAL location of the commit record when recording an async
 * commit.	For a synchronous commit it can be InvalidXLogRecPtr, since the
 * caller guarantees the commit record is already flushed in that case.  It
 * should be InvalidXLogRecPtr for abort cases, too.
 *
 * NB: this is a low-level routine and is NOT the preferred entry point
 * for most uses; TransactionLogUpdate() in transam.c is the intended caller.
 */
void
TransactionIdSetStatus(TransactionId xid, XidStatus status, XLogRecPtr lsn)
{
	int			pageno = TransactionIdToPage(xid);
	int			byteno = TransactionIdToByte(xid);
	int			bshift = TransactionIdToBIndex(xid) * CLOG_BITS_PER_XACT;
	int			slotno;
	char	   *byteptr;
	char		byteval;

	Assert(status == TRANSACTION_STATUS_COMMITTED ||
		   status == TRANSACTION_STATUS_ABORTED ||
		   status == TRANSACTION_STATUS_SUB_COMMITTED);

	LWLockAcquire(CLogControlLock, LW_EXCLUSIVE);

	/*
	 * If we're doing an async commit (ie, lsn is valid), then we must wait
	 * for any active write on the page slot to complete.  Otherwise our
	 * update could reach disk in that write, which will not do since we
	 * mustn't let it reach disk until we've done the appropriate WAL flush.
	 * But when lsn is invalid, it's OK to scribble on a page while it is
	 * write-busy, since we don't care if the update reaches disk sooner than
	 * we think.  Hence, pass write_ok = XLogRecPtrIsInvalid(lsn).
	 */
	slotno = SimpleLruReadPage(ClogCtl, pageno, XLogRecPtrIsInvalid(lsn), xid);
	byteptr = ClogCtl->shared->page_buffer[slotno] + byteno;

	/* Current state should be 0, subcommitted or target state */
	Assert(((*byteptr >> bshift) & CLOG_XACT_BITMASK) == 0 ||
		   ((*byteptr >> bshift) & CLOG_XACT_BITMASK) == TRANSACTION_STATUS_SUB_COMMITTED ||
		   ((*byteptr >> bshift) & CLOG_XACT_BITMASK) == status);

	/* note this assumes exclusive access to the clog page */
	byteval = *byteptr;
	byteval &= ~(((1 << CLOG_BITS_PER_XACT) - 1) << bshift);
	byteval |= (status << bshift);
	*byteptr = byteval;

	ClogCtl->shared->page_dirty[slotno] = true;

	/*
	 * Update the group LSN if the transaction completion LSN is higher.
	 *
	 * Note: lsn will be invalid when supplied during InRecovery processing,
	 * so we don't need to do anything special to avoid LSN updates during
	 * recovery. After recovery completes the next clog change will set the
	 * LSN correctly.
	 */
	if (!XLogRecPtrIsInvalid(lsn))
	{
		int			lsnindex = GetLSNIndex(slotno, xid);

		if (XLByteLT(ClogCtl->shared->group_lsn[lsnindex], lsn))
			ClogCtl->shared->group_lsn[lsnindex] = lsn;
	}

	LWLockRelease(CLogControlLock);
}

/*
 * Interrogate the state of a transaction in the commit log.
 *
 * Aside from the actual commit status, this function returns (into *lsn)
 * an LSN that is late enough to be able to guarantee that if we flush up to
 * that LSN then we will have flushed the transaction's commit record to disk.
 * The result is not necessarily the exact LSN of the transaction's commit
 * record!	For example, for long-past transactions (those whose clog pages
 * already migrated to disk), we'll return InvalidXLogRecPtr.  Also, because
 * we group transactions on the same clog page to conserve storage, we might
 * return the LSN of a later transaction that falls into the same group.
 *
 * NB: this is a low-level routine and is NOT the preferred entry point
 * for most uses; TransactionLogFetch() in transam.c is the intended caller.
 */
XidStatus
TransactionIdGetStatus(TransactionId xid, XLogRecPtr *lsn)
{
	int			pageno = TransactionIdToPage(xid);
	int			byteno = TransactionIdToByte(xid);
	int			bshift = TransactionIdToBIndex(xid) * CLOG_BITS_PER_XACT;
	int			slotno;
	int			lsnindex;
	char	   *byteptr;
	XidStatus	status;

	/* lock is acquired by SimpleLruReadPage_ReadOnly */

	slotno = SimpleLruReadPage_ReadOnly(ClogCtl, pageno, xid);
	byteptr = ClogCtl->shared->page_buffer[slotno] + byteno;

	status = (*byteptr >> bshift) & CLOG_XACT_BITMASK;

	lsnindex = GetLSNIndex(slotno, xid);
	*lsn = ClogCtl->shared->group_lsn[lsnindex];

	LWLockRelease(CLogControlLock);

	return status;
}


/*
 * Initialization of shared memory for CLOG
 */
Size
CLOGShmemSize(void)
{
	return SimpleLruShmemSize(NUM_CLOG_BUFFERS, CLOG_LSNS_PER_PAGE);
}

void
CLOGShmemInit(void)
{
	ClogCtl->PagePrecedes = CLOGPagePrecedes;
	SimpleLruInit(ClogCtl, "CLOG Ctl", NUM_CLOG_BUFFERS, CLOG_LSNS_PER_PAGE,
				  CLogControlLock, "pg_clog");
}

/*
 * This func must be called ONCE on system install.  It creates
 * the initial CLOG segment.  (The CLOG directory is assumed to
 * have been created by the initdb shell script, and CLOGShmemInit
 * must have been called already.)
 */
void
BootStrapCLOG(void)
{
	int			slotno;

	LWLockAcquire(CLogControlLock, LW_EXCLUSIVE);

	/* Create and zero the first page of the commit log */
	slotno = ZeroCLOGPage(0, false);

	/* Make sure it's written out */
	SimpleLruWritePage(ClogCtl, slotno, NULL);
	Assert(!ClogCtl->shared->page_dirty[slotno]);

	LWLockRelease(CLogControlLock);
}

/*
 * Initialize (or reinitialize) a page of CLOG to zeroes.
 * If writeXlog is TRUE, also emit an XLOG record saying we did this.
 *
 * The page is not actually written, just set up in shared memory.
 * The slot number of the new page is returned.
 *
 * Control lock must be held at entry, and will be held at exit.
 */
static int
ZeroCLOGPage(int pageno, bool writeXlog)
{
	int			slotno;

	slotno = SimpleLruZeroPage(ClogCtl, pageno);

	if (writeXlog)
		WriteZeroPageXlogRec(pageno);

	return slotno;
}

/*
 * This must be called ONCE during postmaster or standalone-backend startup,
 * after StartupXLOG has initialized ShmemVariableCache->nextXid.