clog.c File Reference

#include "postgres.h"
#include "access/clog.h"
#include "access/slru.h"
#include "access/transam.h"
#include "access/xlog.h"
#include "access/xloginsert.h"
#include "access/xlogutils.h"
#include "miscadmin.h"
#include "pg_trace.h"
#include "pgstat.h"
#include "storage/proc.h"
#include "storage/sync.h"
#include "utils/guc_hooks.h"

Include dependency graph for clog.c:

Go to the source code of this file.

Macros
#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	CLOG_MAX_ALLOWED_BUFFERS
#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)
#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)
#define	THRESHOLD_SUBTRANS_CLOG_OPT   5
#define	XactCtl   (&XactCtlData)

Functions
static int64	TransactionIdToPage (TransactionId xid)
static bool	CLOGPagePrecedes (int64 page1, int64 page2)
static void	WriteTruncateXlogRec (int64 pageno, TransactionId oldestXact, Oid oldestXactDb)
static void	TransactionIdSetPageStatus (TransactionId xid, int nsubxids, TransactionId *subxids, XidStatus status, XLogRecPtr lsn, int64 pageno, bool all_xact_same_page)
static void	TransactionIdSetStatusBit (TransactionId xid, XidStatus status, XLogRecPtr lsn, int slotno)
static void	set_status_by_pages (int nsubxids, TransactionId *subxids, XidStatus status, XLogRecPtr lsn)
static bool	TransactionGroupUpdateXidStatus (TransactionId xid, XidStatus status, XLogRecPtr lsn, int64 pageno)
static void	TransactionIdSetPageStatusInternal (TransactionId xid, int nsubxids, TransactionId *subxids, XidStatus status, XLogRecPtr lsn, int64 pageno)
void	TransactionIdSetTreeStatus (TransactionId xid, int nsubxids, TransactionId *subxids, XidStatus status, XLogRecPtr lsn)
XidStatus	TransactionIdGetStatus (TransactionId xid, XLogRecPtr *lsn)
static int	CLOGShmemBuffers (void)
Size	CLOGShmemSize (void)
void	CLOGShmemInit (void)
bool	check_transaction_buffers (int *newval, void **extra, GucSource source)
void	BootStrapCLOG (void)
void	StartupCLOG (void)
void	TrimCLOG (void)
void	CheckPointCLOG (void)
void	ExtendCLOG (TransactionId newestXact)
void	TruncateCLOG (TransactionId oldestXact, Oid oldestxid_datoid)
void	clog_redo (XLogReaderState *record)
int	clogsyncfiletag (const FileTag *ftag, char *path)

Variables
static SlruCtlData	XactCtlData

Macro Definition Documentation

CLOG_BITS_PER_XACT

#define CLOG_BITS_PER_XACT   2

Definition at line 62 of file clog.c.

CLOG_LSNS_PER_PAGE

#define CLOG_LSNS_PER_PAGE   (CLOG_XACTS_PER_PAGE / CLOG_XACTS_PER_LSN_GROUP)

Definition at line 93 of file clog.c.

CLOG_MAX_ALLOWED_BUFFERS

#define CLOG_MAX_ALLOWED_BUFFERS

Value:

    Min(SLRU_MAX_ALLOWED_BUFFERS, \
        (((MaxTransactionId / 2) + (CLOG_XACTS_PER_PAGE - 1)) / CLOG_XACTS_PER_PAGE))

Definition at line 72 of file clog.c.

CLOG_XACT_BITMASK

#define CLOG_XACT_BITMASK   ((1 << CLOG_BITS_PER_XACT) - 1)

Definition at line 65 of file clog.c.

CLOG_XACTS_PER_BYTE

#define CLOG_XACTS_PER_BYTE   4

Definition at line 63 of file clog.c.

CLOG_XACTS_PER_LSN_GROUP

#define CLOG_XACTS_PER_LSN_GROUP   32 /* keep this a power of 2 */

Definition at line 92 of file clog.c.

CLOG_XACTS_PER_PAGE

#define CLOG_XACTS_PER_PAGE   (BLCKSZ * CLOG_XACTS_PER_BYTE)

Definition at line 64 of file clog.c.

GetLSNIndex

#define GetLSNIndex	(		slotno,
			xid
	)

Value:

    ((slotno) * CLOG_LSNS_PER_PAGE + \
    ((xid) % (TransactionId) CLOG_XACTS_PER_PAGE) / CLOG_XACTS_PER_LSN_GROUP)

Definition at line 95 of file clog.c.

THRESHOLD_SUBTRANS_CLOG_OPT

#define THRESHOLD_SUBTRANS_CLOG_OPT   5

Definition at line 103 of file clog.c.

TransactionIdToBIndex

#define TransactionIdToBIndex

(

xid

)

((xid) % (TransactionId) CLOG_XACTS_PER_BYTE)

Definition at line 89 of file clog.c.

TransactionIdToByte

#define TransactionIdToByte

(

xid

)

(TransactionIdToPgIndex(xid) / CLOG_XACTS_PER_BYTE)

Definition at line 88 of file clog.c.

TransactionIdToPgIndex

#define TransactionIdToPgIndex

(

xid

)

((xid) % (TransactionId) CLOG_XACTS_PER_PAGE)

Definition at line 87 of file clog.c.

XactCtl

#define XactCtl   (&XactCtlData)

Definition at line 110 of file clog.c.

Function Documentation

BootStrapCLOG()

void BootStrapCLOG

(

void

)

Definition at line 832 of file clog.c.

{
    /* Zero the initial page and flush it to disk */
    SimpleLruZeroAndWritePage(XactCtl, 0);
}

References SimpleLruZeroAndWritePage(), and XactCtl.

Referenced by BootStrapXLOG().

check_transaction_buffers()

bool check_transaction_buffers	(	int *	newval,
		void **	extra,
		GucSource	source
	)

Definition at line 820 of file clog.c.

{
    return check_slru_buffers("transaction_buffers", newval);
}

References check_slru_buffers(), and newval.

CheckPointCLOG()

void CheckPointCLOG

(

void

)

Definition at line 903 of file clog.c.

{
    /*
     * Write dirty CLOG pages to disk.  This may result in sync requests
     * queued for later handling by ProcessSyncRequests(), as part of the
     * checkpoint.
     */
    TRACE_POSTGRESQL_CLOG_CHECKPOINT_START(true);
    SimpleLruWriteAll(XactCtl, true);
    TRACE_POSTGRESQL_CLOG_CHECKPOINT_DONE(true);
}

References SimpleLruWriteAll(), and XactCtl.

Referenced by CheckPointGuts().

clog_redo()

void clog_redo

(

XLogReaderState *

record

)

Definition at line 1063 of file clog.c.

{
    uint8       info = XLogRecGetInfo(record) & ~XLR_INFO_MASK;
 
    /* Backup blocks are not used in clog records */
    Assert(!XLogRecHasAnyBlockRefs(record));
 
    if (info == CLOG_ZEROPAGE)
    {
        int64       pageno;
 
        memcpy(&pageno, XLogRecGetData(record), sizeof(pageno));
        SimpleLruZeroAndWritePage(XactCtl, pageno);
    }
    else if (info == CLOG_TRUNCATE)
    {
        xl_clog_truncate xlrec;
 
        memcpy(&xlrec, XLogRecGetData(record), sizeof(xl_clog_truncate));
 
        AdvanceOldestClogXid(xlrec.oldestXact);
 
        SimpleLruTruncate(XactCtl, xlrec.pageno);
    }
    else
        elog(PANIC, "clog_redo: unknown op code %u", info);
}

References AdvanceOldestClogXid(), Assert(), CLOG_TRUNCATE, CLOG_ZEROPAGE, elog, xl_clog_truncate::oldestXact, xl_clog_truncate::pageno, PANIC, SimpleLruTruncate(), SimpleLruZeroAndWritePage(), XactCtl, XLogRecGetData, XLogRecGetInfo, and XLogRecHasAnyBlockRefs.

CLOGPagePrecedes()

static bool CLOGPagePrecedes ( int64  page1, int64  page2  )

static

Definition at line 1022 of file clog.c.

{
    TransactionId xid1;
    TransactionId xid2;
 
    xid1 = ((TransactionId) page1) * CLOG_XACTS_PER_PAGE;
    xid1 += FirstNormalTransactionId + 1;
    xid2 = ((TransactionId) page2) * CLOG_XACTS_PER_PAGE;
    xid2 += FirstNormalTransactionId + 1;
 
    return (TransactionIdPrecedes(xid1, xid2) &&
            TransactionIdPrecedes(xid1, xid2 + CLOG_XACTS_PER_PAGE - 1));
}

References CLOG_XACTS_PER_PAGE, FirstNormalTransactionId, and TransactionIdPrecedes().

Referenced by CLOGShmemInit().

CLOGShmemBuffers()

static int CLOGShmemBuffers ( void  )

static

Definition at line 767 of file clog.c.

{
    /* auto-tune based on shared buffers */
    if (transaction_buffers == 0)
        return SimpleLruAutotuneBuffers(512, 1024);
 
    return Min(Max(16, transaction_buffers), CLOG_MAX_ALLOWED_BUFFERS);
}

References CLOG_MAX_ALLOWED_BUFFERS, Max, Min, SimpleLruAutotuneBuffers(), and transaction_buffers.

Referenced by CLOGShmemInit(), and CLOGShmemSize().

CLOGShmemInit()

void CLOGShmemInit

(

void

)

Definition at line 786 of file clog.c.

{
    /* If auto-tuning is requested, now is the time to do it */
    if (transaction_buffers == 0)
    {
        char        buf[32];
 
        snprintf(buf, sizeof(buf), "%d", CLOGShmemBuffers());
        SetConfigOption("transaction_buffers", buf, PGC_POSTMASTER,
                        PGC_S_DYNAMIC_DEFAULT);
 
        /*
         * We prefer to report this value's source as PGC_S_DYNAMIC_DEFAULT.
         * However, if the DBA explicitly set transaction_buffers = 0 in the
         * config file, then PGC_S_DYNAMIC_DEFAULT will fail to override that
         * and we must force the matter with PGC_S_OVERRIDE.
         */
        if (transaction_buffers == 0)   /* failed to apply it? */
            SetConfigOption("transaction_buffers", buf, PGC_POSTMASTER,
                            PGC_S_OVERRIDE);
    }
    Assert(transaction_buffers != 0);
 
    XactCtl->PagePrecedes = CLOGPagePrecedes;
    SimpleLruInit(XactCtl, "transaction", CLOGShmemBuffers(), CLOG_LSNS_PER_PAGE,
                  "pg_xact", LWTRANCHE_XACT_BUFFER,
                  LWTRANCHE_XACT_SLRU, SYNC_HANDLER_CLOG, false);
    SlruPagePrecedesUnitTests(XactCtl, CLOG_XACTS_PER_PAGE);
}

References Assert(), buf, CLOG_LSNS_PER_PAGE, CLOG_XACTS_PER_PAGE, CLOGPagePrecedes(), CLOGShmemBuffers(), PGC_POSTMASTER, PGC_S_DYNAMIC_DEFAULT, PGC_S_OVERRIDE, SetConfigOption(), SimpleLruInit(), SlruPagePrecedesUnitTests, snprintf, SYNC_HANDLER_CLOG, transaction_buffers, and XactCtl.

Referenced by CreateOrAttachShmemStructs().

CLOGShmemSize()

Size CLOGShmemSize

(

void

)

Definition at line 780 of file clog.c.

{
    return SimpleLruShmemSize(CLOGShmemBuffers(), CLOG_LSNS_PER_PAGE);
}

References CLOG_LSNS_PER_PAGE, CLOGShmemBuffers(), and SimpleLruShmemSize().

Referenced by CalculateShmemSize().

clogsyncfiletag()

int clogsyncfiletag	(	const FileTag *	ftag,
		char *	path
	)

Definition at line 1095 of file clog.c.

{
    return SlruSyncFileTag(XactCtl, ftag, path);
}

References SlruSyncFileTag(), and XactCtl.

ExtendCLOG()

void ExtendCLOG

(

TransactionId

newestXact

)

Definition at line 925 of file clog.c.

{
    int64       pageno;
    LWLock     *lock;
 
    /*
     * No work except at first XID of a page.  But beware: just after
     * wraparound, the first XID of page zero is FirstNormalTransactionId.
     */
    if (TransactionIdToPgIndex(newestXact) != 0 &&
        !TransactionIdEquals(newestXact, FirstNormalTransactionId))
        return;
 
    pageno = TransactionIdToPage(newestXact);
    lock = SimpleLruGetBankLock(XactCtl, pageno);
 
    LWLockAcquire(lock, LW_EXCLUSIVE);
 
    /* Zero the page and make a WAL entry about it */
    SimpleLruZeroPage(XactCtl, pageno);
    XLogSimpleInsertInt64(RM_CLOG_ID, CLOG_ZEROPAGE, pageno);
 
    LWLockRelease(lock);
}

References CLOG_ZEROPAGE, FirstNormalTransactionId, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), SimpleLruGetBankLock(), SimpleLruZeroPage(), TransactionIdEquals, TransactionIdToPage(), TransactionIdToPgIndex, XactCtl, and XLogSimpleInsertInt64().

Referenced by GetNewTransactionId().

set_status_by_pages()

static void set_status_by_pages ( int  nsubxids, TransactionId *  subxids, XidStatus  status, XLogRecPtr  lsn  )

static

Definition at line 255 of file clog.c.

{
    int64       pageno = TransactionIdToPage(subxids[0]);
    int         offset = 0;
    int         i = 0;
 
    Assert(nsubxids > 0);       /* else the pageno fetch above is unsafe */
 
    while (i < nsubxids)
    {
        int         num_on_page = 0;
        int64       nextpageno;
 
        do
        {
            nextpageno = TransactionIdToPage(subxids[i]);
            if (nextpageno != pageno)
                break;
            num_on_page++;
            i++;
        } while (i < nsubxids);
 
        TransactionIdSetPageStatus(InvalidTransactionId,
                                   num_on_page, subxids + offset,
                                   status, lsn, pageno, false);
        offset = i;
        pageno = nextpageno;
    }
}

References Assert(), i, InvalidTransactionId, TransactionIdSetPageStatus(), and TransactionIdToPage().

Referenced by TransactionIdSetTreeStatus().

StartupCLOG()

void StartupCLOG

(

void

)

Definition at line 843 of file clog.c.

{
    TransactionId xid = XidFromFullTransactionId(TransamVariables->nextXid);
    int64       pageno = TransactionIdToPage(xid);
 
    /*
     * Initialize our idea of the latest page number.
     */
    pg_atomic_write_u64(&XactCtl->shared->latest_page_number, pageno);
}

References TransamVariablesData::nextXid, pg_atomic_write_u64(), TransactionIdToPage(), TransamVariables, XactCtl, and XidFromFullTransactionId.

Referenced by StartupXLOG().

TransactionGroupUpdateXidStatus()

static bool TransactionGroupUpdateXidStatus ( TransactionId  xid, XidStatus  status, XLogRecPtr  lsn, int64  pageno  )

static

Definition at line 440 of file clog.c.

{
    volatile PROC_HDR *procglobal = ProcGlobal;
    PGPROC     *proc = MyProc;
    uint32      nextidx;
    uint32      wakeidx;
    int64       prevpageno;
    LWLock     *prevlock = NULL;
 
    /* We should definitely have an XID whose status needs to be updated. */
    Assert(TransactionIdIsValid(xid));
 
    /*
     * Prepare to add ourselves to the list of processes needing a group XID
     * status update.
     */
    proc->clogGroupMember = true;
    proc->clogGroupMemberXid = xid;
    proc->clogGroupMemberXidStatus = status;
    proc->clogGroupMemberPage = pageno;
    proc->clogGroupMemberLsn = lsn;
 
    /*
     * We put ourselves in the queue by writing MyProcNumber to
     * ProcGlobal->clogGroupFirst.  However, if there's already a process
     * listed there, we compare our pageno with that of that process; if it
     * differs, we cannot participate in the group, so we return for caller to
     * update pg_xact in the normal way.
     *
     * If we're not the first process in the list, we must follow the leader.
     * We do this by storing the data we want updated in our PGPROC entry
     * where the leader can find it, then going to sleep.
     *
     * If no process is already in the list, we're the leader; our first step
     * is to lock the SLRU bank to which our page belongs, then we close out
     * the group by resetting the list pointer from ProcGlobal->clogGroupFirst
     * (this lets other processes set up other groups later); finally we do
     * the SLRU updates, release the SLRU bank lock, and wake up the sleeping
     * processes.
     *
     * If another group starts to update a page in a different SLRU bank, they
     * can proceed concurrently, since the bank lock they're going to use is
     * different from ours.  If another group starts to update a page in the
     * same bank as ours, they wait until we release the lock.
     */
    nextidx = pg_atomic_read_u32(&procglobal->clogGroupFirst);
 
    while (true)
    {
        /*
         * Add the proc to list, if the clog page where we need to update the
         * current transaction status is same as group leader's clog page.
         *
         * There is a race condition here, which is that after doing the below
         * check and before adding this proc's clog update to a group, the
         * group leader might have already finished the group update for this
         * page and becomes group leader of another group, updating a
         * different page.  This will lead to a situation where a single group
         * can have different clog page updates.  This isn't likely and will
         * still work, just less efficiently -- we handle this case by
         * switching to a different bank lock in the loop below.
         */
        if (nextidx != INVALID_PROC_NUMBER &&
            GetPGProcByNumber(nextidx)->clogGroupMemberPage != proc->clogGroupMemberPage)
        {
            /*
             * Ensure that this proc is not a member of any clog group that
             * needs an XID status update.
             */
            proc->clogGroupMember = false;
            pg_atomic_write_u32(&proc->clogGroupNext, INVALID_PROC_NUMBER);
            return false;
        }
 
        pg_atomic_write_u32(&proc->clogGroupNext, nextidx);
 
        if (pg_atomic_compare_exchange_u32(&procglobal->clogGroupFirst,
                                           &nextidx,
                                           (uint32) MyProcNumber))
            break;
    }
 
    /*
     * If the list was not empty, the leader will update the status of our
     * XID. It is impossible to have followers without a leader because the
     * first process that has added itself to the list will always have
     * nextidx as INVALID_PROC_NUMBER.
     */
    if (nextidx != INVALID_PROC_NUMBER)
    {
        int         extraWaits = 0;
 
        /* Sleep until the leader updates our XID status. */
        pgstat_report_wait_start(WAIT_EVENT_XACT_GROUP_UPDATE);
        for (;;)
        {
            /* acts as a read barrier */
            PGSemaphoreLock(proc->sem);
            if (!proc->clogGroupMember)
                break;
            extraWaits++;
        }
        pgstat_report_wait_end();
 
        Assert(pg_atomic_read_u32(&proc->clogGroupNext) == INVALID_PROC_NUMBER);
 
        /* Fix semaphore count for any absorbed wakeups */
        while (extraWaits-- > 0)
            PGSemaphoreUnlock(proc->sem);
        return true;
    }
 
    /*
     * By here, we know we're the leader process.  Acquire the SLRU bank lock
     * that corresponds to the page we originally wanted to modify.
     */
    prevpageno = proc->clogGroupMemberPage;
    prevlock = SimpleLruGetBankLock(XactCtl, prevpageno);
    LWLockAcquire(prevlock, LW_EXCLUSIVE);
 
    /*
     * Now that we've got the lock, clear the list of processes waiting for
     * group XID status update, saving a pointer to the head of the list.
     * (Trying to pop elements one at a time could lead to an ABA problem.)
     *
     * At this point, any processes trying to do this would create a separate
     * group.
     */
    nextidx = pg_atomic_exchange_u32(&procglobal->clogGroupFirst,
                                     INVALID_PROC_NUMBER);
 
    /* Remember head of list so we can perform wakeups after dropping lock. */
    wakeidx = nextidx;
 
    /* Walk the list and update the status of all XIDs. */
    while (nextidx != INVALID_PROC_NUMBER)
    {
        PGPROC     *nextproc = &ProcGlobal->allProcs[nextidx];
        int64       thispageno = nextproc->clogGroupMemberPage;
 
        /*
         * If the page to update belongs to a different bank than the previous
         * one, exchange bank lock to the new one.  This should be quite rare,
         * as described above.
         *
         * (We could try to optimize this by waking up the processes for which
         * we have already updated the status while we exchange the lock, but
         * the code doesn't do that at present.  I think it'd require
         * additional bookkeeping, making the common path slower in order to
         * improve an infrequent case.)
         */
        if (thispageno != prevpageno)
        {
            LWLock     *lock = SimpleLruGetBankLock(XactCtl, thispageno);
 
            if (prevlock != lock)
            {
                LWLockRelease(prevlock);
                LWLockAcquire(lock, LW_EXCLUSIVE);
            }
            prevlock = lock;
            prevpageno = thispageno;
        }
 
        /*
         * Transactions with more than THRESHOLD_SUBTRANS_CLOG_OPT sub-XIDs
         * should not use group XID status update mechanism.
         */
        Assert(nextproc->subxidStatus.count <= THRESHOLD_SUBTRANS_CLOG_OPT);
 
        TransactionIdSetPageStatusInternal(nextproc->clogGroupMemberXid,
                                           nextproc->subxidStatus.count,
                                           nextproc->subxids.xids,
                                           nextproc->clogGroupMemberXidStatus,
                                           nextproc->clogGroupMemberLsn,
                                           nextproc->clogGroupMemberPage);
 
        /* Move to next proc in list. */
        nextidx = pg_atomic_read_u32(&nextproc->clogGroupNext);
    }
 
    /* We're done with the lock now. */
    if (prevlock != NULL)
        LWLockRelease(prevlock);
 
    /*
     * Now that we've released the lock, go back and wake everybody up.  We
     * don't do this under the lock so as to keep lock hold times to a
     * minimum.
     *
     * (Perhaps we could do this in two passes, the first setting
     * clogGroupNext to invalid while saving the semaphores to an array, then
     * a single write barrier, then another pass unlocking the semaphores.)
     */
    while (wakeidx != INVALID_PROC_NUMBER)
    {
        PGPROC     *wakeproc = &ProcGlobal->allProcs[wakeidx];
 
        wakeidx = pg_atomic_read_u32(&wakeproc->clogGroupNext);
        pg_atomic_write_u32(&wakeproc->clogGroupNext, INVALID_PROC_NUMBER);
 
        /* ensure all previous writes are visible before follower continues. */
        pg_write_barrier();
 
        wakeproc->clogGroupMember = false;
 
        if (wakeproc != MyProc)
            PGSemaphoreUnlock(wakeproc->sem);
    }
 
    return true;
}

References PROC_HDR::allProcs, Assert(), PROC_HDR::clogGroupFirst, PGPROC::clogGroupMember, PGPROC::clogGroupMemberLsn, PGPROC::clogGroupMemberPage, PGPROC::clogGroupMemberXid, PGPROC::clogGroupMemberXidStatus, PGPROC::clogGroupNext, XidCacheStatus::count, GetPGProcByNumber, INVALID_PROC_NUMBER, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), MyProc, MyProcNumber, pg_atomic_compare_exchange_u32(), pg_atomic_exchange_u32(), pg_atomic_read_u32(), pg_atomic_write_u32(), pg_write_barrier, PGSemaphoreLock(), PGSemaphoreUnlock(), pgstat_report_wait_end(), pgstat_report_wait_start(), ProcGlobal, PGPROC::sem, SimpleLruGetBankLock(), PGPROC::subxids, PGPROC::subxidStatus, THRESHOLD_SUBTRANS_CLOG_OPT, TransactionIdIsValid, TransactionIdSetPageStatusInternal(), XactCtl, and XidCache::xids.

Referenced by TransactionIdSetPageStatus().

TransactionIdGetStatus()

XidStatus TransactionIdGetStatus	(	TransactionId	xid,
		XLogRecPtr *	lsn
	)

Definition at line 734 of file clog.c.

{
    int64       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(XactCtl, pageno, xid);
    byteptr = XactCtl->shared->page_buffer[slotno] + byteno;
 
    status = (*byteptr >> bshift) & CLOG_XACT_BITMASK;
 
    lsnindex = GetLSNIndex(slotno, xid);
    *lsn = XactCtl->shared->group_lsn[lsnindex];
 
    LWLockRelease(SimpleLruGetBankLock(XactCtl, pageno));
 
    return status;
}

References CLOG_BITS_PER_XACT, CLOG_XACT_BITMASK, GetLSNIndex, LWLockRelease(), SimpleLruGetBankLock(), SimpleLruReadPage_ReadOnly(), TransactionIdToBIndex, TransactionIdToByte, TransactionIdToPage(), and XactCtl.

Referenced by TransactionIdGetCommitLSN(), and TransactionLogFetch().

TransactionIdSetPageStatus()

static void TransactionIdSetPageStatus ( TransactionId  xid, int  nsubxids, TransactionId *  subxids, XidStatus  status, XLogRecPtr  lsn, int64  pageno, bool  all_xact_same_page  )

static

Definition at line 291 of file clog.c.

{
    LWLock     *lock;
 
    /* Can't use group update when PGPROC overflows. */
    StaticAssertDecl(THRESHOLD_SUBTRANS_CLOG_OPT <= PGPROC_MAX_CACHED_SUBXIDS,
                     "group clog threshold less than PGPROC cached subxids");
 
    /* Get the SLRU bank lock for the page we are going to access. */
    lock = SimpleLruGetBankLock(XactCtl, pageno);
 
    /*
     * When there is contention on the SLRU bank lock we need, we try to group
     * multiple updates; a single leader process will perform transaction
     * status updates for multiple backends so that the number of times the
     * bank lock needs to be acquired is reduced.
     *
     * For this optimization to be safe, the XID and subxids in MyProc must be
     * the same as the ones for which we're setting the status.  Check that
     * this is the case.
     *
     * For this optimization to be efficient, we shouldn't have too many
     * sub-XIDs and all of the XIDs for which we're adjusting clog should be
     * on the same page.  Check those conditions, too.
     */
    if (all_xact_same_page && xid == MyProc->xid &&
        nsubxids <= THRESHOLD_SUBTRANS_CLOG_OPT &&
        nsubxids == MyProc->subxidStatus.count &&
        (nsubxids == 0 ||
         memcmp(subxids, MyProc->subxids.xids,
                nsubxids * sizeof(TransactionId)) == 0))
    {
        /*
         * If we can immediately acquire the lock, we update the status of our
         * own XID and release the lock.  If not, try use group XID update. If
         * that doesn't work out, fall back to waiting for the lock to perform
         * an update for this transaction only.
         */
        if (LWLockConditionalAcquire(lock, LW_EXCLUSIVE))
        {
            /* Got the lock without waiting!  Do the update. */
            TransactionIdSetPageStatusInternal(xid, nsubxids, subxids, status,
                                               lsn, pageno);
            LWLockRelease(lock);
            return;
        }
        else if (TransactionGroupUpdateXidStatus(xid, status, lsn, pageno))
        {
            /* Group update mechanism has done the work. */
            return;
        }
 
        /* Fall through only if update isn't done yet. */
    }
 
    /* Group update not applicable, or couldn't accept this page number. */
    LWLockAcquire(lock, LW_EXCLUSIVE);
    TransactionIdSetPageStatusInternal(xid, nsubxids, subxids, status,
                                       lsn, pageno);
    LWLockRelease(lock);
}

References XidCacheStatus::count, LW_EXCLUSIVE, LWLockAcquire(), LWLockConditionalAcquire(), LWLockRelease(), MyProc, PGPROC_MAX_CACHED_SUBXIDS, SimpleLruGetBankLock(), StaticAssertDecl, PGPROC::subxids, PGPROC::subxidStatus, THRESHOLD_SUBTRANS_CLOG_OPT, TransactionGroupUpdateXidStatus(), TransactionIdSetPageStatusInternal(), XactCtl, PGPROC::xid, and XidCache::xids.

Referenced by set_status_by_pages(), and TransactionIdSetTreeStatus().

TransactionIdSetPageStatusInternal()

static void TransactionIdSetPageStatusInternal ( TransactionId  xid, int  nsubxids, TransactionId *  subxids, XidStatus  status, XLogRecPtr  lsn, int64  pageno  )

static

Definition at line 362 of file clog.c.

{
    int         slotno;
    int         i;
 
    Assert(status == TRANSACTION_STATUS_COMMITTED ||
           status == TRANSACTION_STATUS_ABORTED ||
           (status == TRANSACTION_STATUS_SUB_COMMITTED && !TransactionIdIsValid(xid)));
    Assert(LWLockHeldByMeInMode(SimpleLruGetBankLock(XactCtl, pageno),
                                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.
     */
    slotno = SimpleLruReadPage(XactCtl, pageno, !XLogRecPtrIsValid(lsn),
                               xid);
 
    /*
     * Set the main transaction id, if any.
     *
     * If we update more than one xid on this page while it is being written
     * out, we might find that some of the bits go to disk and others don't.
     * If we are updating commits on the page with the top-level xid that
     * could break atomicity, so we subcommit the subxids first before we mark
     * the top-level commit.
     */
    if (TransactionIdIsValid(xid))
    {
        /* Subtransactions first, if needed ... */
        if (status == TRANSACTION_STATUS_COMMITTED)
        {
            for (i = 0; i < nsubxids; i++)
            {
                Assert(XactCtl->shared->page_number[slotno] == TransactionIdToPage(subxids[i]));
                TransactionIdSetStatusBit(subxids[i],
                                          TRANSACTION_STATUS_SUB_COMMITTED,
                                          lsn, slotno);
            }
        }
 
        /* ... then the main transaction */
        TransactionIdSetStatusBit(xid, status, lsn, slotno);
    }
 
    /* Set the subtransactions */
    for (i = 0; i < nsubxids; i++)
    {
        Assert(XactCtl->shared->page_number[slotno] == TransactionIdToPage(subxids[i]));
        TransactionIdSetStatusBit(subxids[i], status, lsn, slotno);
    }
 
    XactCtl->shared->page_dirty[slotno] = true;
}

References Assert(), i, LW_EXCLUSIVE, LWLockHeldByMeInMode(), SimpleLruGetBankLock(), SimpleLruReadPage(), TRANSACTION_STATUS_ABORTED, TRANSACTION_STATUS_COMMITTED, TRANSACTION_STATUS_SUB_COMMITTED, TransactionIdIsValid, TransactionIdSetStatusBit(), TransactionIdToPage(), XactCtl, and XLogRecPtrIsValid.

Referenced by TransactionGroupUpdateXidStatus(), and TransactionIdSetPageStatus().

TransactionIdSetStatusBit()

static void TransactionIdSetStatusBit ( TransactionId  xid, XidStatus  status, XLogRecPtr  lsn, int  slotno  )

static

Definition at line 660 of file clog.c.

{
    int         byteno = TransactionIdToByte(xid);
    int         bshift = TransactionIdToBIndex(xid) * CLOG_BITS_PER_XACT;
    char       *byteptr;
    char        byteval;
    char        curval;
 
    Assert(XactCtl->shared->page_number[slotno] == TransactionIdToPage(xid));
    Assert(LWLockHeldByMeInMode(SimpleLruGetBankLock(XactCtl,
                                                     XactCtl->shared->page_number[slotno]),
                                LW_EXCLUSIVE));
 
    byteptr = XactCtl->shared->page_buffer[slotno] + byteno;
    curval = (*byteptr >> bshift) & CLOG_XACT_BITMASK;
 
    /*
     * When replaying transactions during recovery we still need to perform
     * the two phases of subcommit and then commit. However, some transactions
     * are already correctly marked, so we just treat those as a no-op which
     * allows us to keep the following Assert as restrictive as possible.
     */
    if (InRecovery && status == TRANSACTION_STATUS_SUB_COMMITTED &&
        curval == TRANSACTION_STATUS_COMMITTED)
        return;
 
    /*
     * Current state change should be from 0 or subcommitted to target state
     * or we should already be there when replaying changes during recovery.
     */
    Assert(curval == 0 ||
           (curval == TRANSACTION_STATUS_SUB_COMMITTED &&
            status != TRANSACTION_STATUS_IN_PROGRESS) ||
           curval == 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;
 
    /*
     * 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 (XLogRecPtrIsValid(lsn))
    {
        int         lsnindex = GetLSNIndex(slotno, xid);
 
        if (XactCtl->shared->group_lsn[lsnindex] < lsn)
            XactCtl->shared->group_lsn[lsnindex] = lsn;
    }
}

References Assert(), CLOG_BITS_PER_XACT, CLOG_XACT_BITMASK, GetLSNIndex, InRecovery, LW_EXCLUSIVE, LWLockHeldByMeInMode(), SimpleLruGetBankLock(), TRANSACTION_STATUS_COMMITTED, TRANSACTION_STATUS_IN_PROGRESS, TRANSACTION_STATUS_SUB_COMMITTED, TransactionIdToBIndex, TransactionIdToByte, TransactionIdToPage(), XactCtl, and XLogRecPtrIsValid.

Referenced by TransactionIdSetPageStatusInternal().

TransactionIdSetTreeStatus()

void TransactionIdSetTreeStatus	(	TransactionId	xid,
		int	nsubxids,
		TransactionId *	subxids,
		XidStatus	status,
		XLogRecPtr	lsn
	)

Definition at line 181 of file clog.c.

{
    int64       pageno = TransactionIdToPage(xid);  /* get page of parent */
    int         i;
 
    Assert(status == TRANSACTION_STATUS_COMMITTED ||
           status == TRANSACTION_STATUS_ABORTED);
 
    /*
     * See how many subxids, if any, are on the same page as the parent, if
     * any.
     */
    for (i = 0; i < nsubxids; i++)
    {
        if (TransactionIdToPage(subxids[i]) != pageno)
            break;
    }
 
    /*
     * Do all items fit on a single page?
     */
    if (i == nsubxids)
    {
        /*
         * Set the parent and all subtransactions in a single call
         */
        TransactionIdSetPageStatus(xid, nsubxids, subxids, status, lsn,
                                   pageno, true);
    }
    else
    {
        int         nsubxids_on_first_page = i;
 
        /*
         * If this is a commit then we care about doing this correctly (i.e.
         * using the subcommitted intermediate status).  By here, we know
         * we're updating more than one page of clog, so we must mark entries
         * that are *not* on the first page so that they show as subcommitted
         * before we then return to update the status to fully committed.
         *
         * To avoid touching the first page twice, skip marking subcommitted
         * for the subxids on that first page.
         */
        if (status == TRANSACTION_STATUS_COMMITTED)
            set_status_by_pages(nsubxids - nsubxids_on_first_page,
                                subxids + nsubxids_on_first_page,
                                TRANSACTION_STATUS_SUB_COMMITTED, lsn);
 
        /*
         * Now set the parent and subtransactions on same page as the parent,
         * if any
         */
        pageno = TransactionIdToPage(xid);
        TransactionIdSetPageStatus(xid, nsubxids_on_first_page, subxids, status,
                                   lsn, pageno, false);
 
        /*
         * Now work through the rest of the subxids one clog page at a time,
         * starting from the second page onwards, like we did above.
         */
        set_status_by_pages(nsubxids - nsubxids_on_first_page,
                            subxids + nsubxids_on_first_page,
                            status, lsn);
    }
}

References Assert(), i, set_status_by_pages(), TRANSACTION_STATUS_ABORTED, TRANSACTION_STATUS_COMMITTED, TRANSACTION_STATUS_SUB_COMMITTED, TransactionIdSetPageStatus(), and TransactionIdToPage().

Referenced by TransactionIdAbortTree(), TransactionIdAsyncCommitTree(), and TransactionIdCommitTree().

TransactionIdToPage()

static int64 TransactionIdToPage ( TransactionId  xid )

inlinestatic

Definition at line 82 of file clog.c.

{
    return xid / (int64) CLOG_XACTS_PER_PAGE;
}

References CLOG_XACTS_PER_PAGE.

Referenced by ExtendCLOG(), set_status_by_pages(), StartupCLOG(), TransactionIdGetStatus(), TransactionIdSetPageStatusInternal(), TransactionIdSetStatusBit(), TransactionIdSetTreeStatus(), TrimCLOG(), and TruncateCLOG().

TrimCLOG()

void TrimCLOG

(

void

)

Definition at line 858 of file clog.c.

{
    TransactionId xid = XidFromFullTransactionId(TransamVariables->nextXid);
    int64       pageno = TransactionIdToPage(xid);
    LWLock     *lock = SimpleLruGetBankLock(XactCtl, pageno);
 
    LWLockAcquire(lock, LW_EXCLUSIVE);
 
    /*
     * Zero out the remainder of the current clog page.  Under normal
     * circumstances it should be zeroes already, but it seems at least
     * theoretically possible that XLOG replay will have settled on a nextXID
     * value that is less than the last XID actually used and marked by the
     * previous database lifecycle (since subtransaction commit writes clog
     * but makes no WAL entry).  Let's just be safe. (We need not worry about
     * pages beyond the current one, since those will be zeroed when first
     * used.  For the same reason, there is no need to do anything when
     * nextXid is exactly at a page boundary; and it's likely that the
     * "current" page doesn't exist yet in that case.)
     */
    if (TransactionIdToPgIndex(xid) != 0)
    {
        int         byteno = TransactionIdToByte(xid);
        int         bshift = TransactionIdToBIndex(xid) * CLOG_BITS_PER_XACT;
        int         slotno;
        char       *byteptr;
 
        slotno = SimpleLruReadPage(XactCtl, pageno, false, xid);
        byteptr = XactCtl->shared->page_buffer[slotno] + byteno;
 
        /* Zero so-far-unused positions in the current byte */
        *byteptr &= (1 << bshift) - 1;
        /* Zero the rest of the page */
        MemSet(byteptr + 1, 0, BLCKSZ - byteno - 1);
 
        XactCtl->shared->page_dirty[slotno] = true;
    }
 
    LWLockRelease(lock);
}

References CLOG_BITS_PER_XACT, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), MemSet, TransamVariablesData::nextXid, SimpleLruGetBankLock(), SimpleLruReadPage(), TransactionIdToBIndex, TransactionIdToByte, TransactionIdToPage(), TransactionIdToPgIndex, TransamVariables, XactCtl, and XidFromFullTransactionId.

Referenced by StartupXLOG().

TruncateCLOG()

void TruncateCLOG	(	TransactionId	oldestXact,
		Oid	oldestxid_datoid
	)

Definition at line 967 of file clog.c.

{
    int64       cutoffPage;
 
    /*
     * The cutoff point is the start of the segment containing oldestXact. We
     * pass the *page* containing oldestXact to SimpleLruTruncate.
     */
    cutoffPage = TransactionIdToPage(oldestXact);
 
    /* Check to see if there's any files that could be removed */
    if (!SlruScanDirectory(XactCtl, SlruScanDirCbReportPresence, &cutoffPage))
        return;                 /* nothing to remove */
 
    /*
     * Advance oldestClogXid before truncating clog, so concurrent xact status
     * lookups can ensure they don't attempt to access truncated-away clog.
     *
     * It's only necessary to do this if we will actually truncate away clog
     * pages.
     */
    AdvanceOldestClogXid(oldestXact);
 
    /*
     * Write XLOG record and flush XLOG to disk. We record the oldest xid
     * we're keeping information about here so we can ensure that it's always
     * ahead of clog truncation in case we crash, and so a standby finds out
     * the new valid xid before the next checkpoint.
     */
    WriteTruncateXlogRec(cutoffPage, oldestXact, oldestxid_datoid);
 
    /* Now we can remove the old CLOG segment(s) */
    SimpleLruTruncate(XactCtl, cutoffPage);
}

References AdvanceOldestClogXid(), SimpleLruTruncate(), SlruScanDirCbReportPresence(), SlruScanDirectory(), TransactionIdToPage(), WriteTruncateXlogRec(), and XactCtl.

Referenced by vac_truncate_clog().

WriteTruncateXlogRec()

static void WriteTruncateXlogRec ( int64  pageno, TransactionId  oldestXact, Oid  oldestXactDb  )

static

Definition at line 1044 of file clog.c.

{
    XLogRecPtr  recptr;
    xl_clog_truncate xlrec;
 
    xlrec.pageno = pageno;
    xlrec.oldestXact = oldestXact;
    xlrec.oldestXactDb = oldestXactDb;
 
    XLogBeginInsert();
    XLogRegisterData(&xlrec, sizeof(xl_clog_truncate));
    recptr = XLogInsert(RM_CLOG_ID, CLOG_TRUNCATE);
    XLogFlush(recptr);
}

References CLOG_TRUNCATE, xl_clog_truncate::oldestXact, xl_clog_truncate::oldestXactDb, xl_clog_truncate::pageno, XLogBeginInsert(), XLogFlush(), XLogInsert(), and XLogRegisterData().

Referenced by TruncateCLOG().

Variable Documentation

XactCtlData

SlruCtlData XactCtlData

static

Definition at line 108 of file clog.c.