checkpointer.c File Reference

#include "postgres.h"
#include <sys/time.h>
#include "access/xlog.h"
#include "access/xlog_internal.h"
#include "access/xlogrecovery.h"
#include "catalog/pg_authid.h"
#include "commands/defrem.h"
#include "libpq/pqsignal.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "postmaster/auxprocess.h"
#include "postmaster/bgwriter.h"
#include "postmaster/interrupt.h"
#include "replication/syncrep.h"
#include "storage/aio_subsys.h"
#include "storage/bufmgr.h"
#include "storage/condition_variable.h"
#include "storage/fd.h"
#include "storage/ipc.h"
#include "storage/lwlock.h"
#include "storage/pmsignal.h"
#include "storage/proc.h"
#include "storage/procsignal.h"
#include "storage/shmem.h"
#include "storage/smgr.h"
#include "storage/spin.h"
#include "utils/acl.h"
#include "utils/guc.h"
#include "utils/memutils.h"
#include "utils/resowner.h"

Include dependency graph for checkpointer.c:

Go to the source code of this file.

Data Structures
struct	CheckpointerRequest
struct	CheckpointerShmemStruct

Macros
#define	WRITES_PER_ABSORB   1000
#define	CKPT_REQ_BATCH_SIZE   10000
#define	MAX_CHECKPOINT_REQUESTS   10000000
#define	MAX_SIGNAL_TRIES   600 /* max wait 60.0 sec */

Functions
static void	ProcessCheckpointerInterrupts (void)
static void	CheckArchiveTimeout (void)
static bool	IsCheckpointOnSchedule (double progress)
static bool	FastCheckpointRequested (void)
static bool	CompactCheckpointerRequestQueue (void)
static void	UpdateSharedMemoryConfig (void)
static void	ReqShutdownXLOG (SIGNAL_ARGS)
void	CheckpointerMain (const void *startup_data, size_t startup_data_len)
void	CheckpointWriteDelay (int flags, double progress)
Size	CheckpointerShmemSize (void)
void	CheckpointerShmemInit (void)
void	ExecCheckpoint (ParseState *pstate, CheckPointStmt *stmt)
void	RequestCheckpoint (int flags)
bool	ForwardSyncRequest (const FileTag *ftag, SyncRequestType type)
void	AbsorbSyncRequests (void)
bool	FirstCallSinceLastCheckpoint (void)
void	WakeupCheckpointer (void)

Variables
static CheckpointerShmemStruct *	CheckpointerShmem
int	CheckPointTimeout = 300
int	CheckPointWarning = 30
double	CheckPointCompletionTarget = 0.9
static bool	ckpt_active = false
static volatile sig_atomic_t	ShutdownXLOGPending = false
static pg_time_t	ckpt_start_time
static XLogRecPtr	ckpt_start_recptr
static double	ckpt_cached_elapsed
static pg_time_t	last_checkpoint_time
static pg_time_t	last_xlog_switch_time

Macro Definition Documentation

CKPT_REQ_BATCH_SIZE

#define CKPT_REQ_BATCH_SIZE   10000

Definition at line 149 of file checkpointer.c.

MAX_CHECKPOINT_REQUESTS

#define MAX_CHECKPOINT_REQUESTS   10000000

Definition at line 152 of file checkpointer.c.

MAX_SIGNAL_TRIES

#define MAX_SIGNAL_TRIES   600 /* max wait 60.0 sec */

WRITES_PER_ABSORB

#define WRITES_PER_ABSORB   1000

Definition at line 146 of file checkpointer.c.

Function Documentation

AbsorbSyncRequests()

void AbsorbSyncRequests

(

void

)

Definition at line 1437 of file checkpointer.c.

{
    CheckpointerRequest *requests = NULL;
    CheckpointerRequest *request;
    int         n,
                i;
    bool        loop;
 
    if (!AmCheckpointerProcess())
        return;
 
    do
    {
        LWLockAcquire(CheckpointerCommLock, LW_EXCLUSIVE);
 
        /*---
         * We try to avoid holding the lock for a long time by:
         * 1. Copying the request array and processing the requests after
         *    releasing the lock;
         * 2. Processing not the whole queue, but only batches of
         *    CKPT_REQ_BATCH_SIZE at once.
         *
         * Once we have cleared the requests from shared memory, we must
         * PANIC if we then fail to absorb them (e.g., because our hashtable
         * runs out of memory).  This is because the system cannot run safely
         * if we are unable to fsync what we have been told to fsync.
         * Fortunately, the hashtable is so small that the problem is quite
         * unlikely to arise in practice.
         *
         * Note: The maximum possible size of a ring buffer is
         * MAX_CHECKPOINT_REQUESTS entries, which fit into a maximum palloc
         * allocation size of 1Gb.  Our maximum batch size,
         * CKPT_REQ_BATCH_SIZE, is even smaller.
         */
        n = Min(CheckpointerShmem->num_requests, CKPT_REQ_BATCH_SIZE);
        if (n > 0)
        {
            if (!requests)
                requests = (CheckpointerRequest *) palloc(n * sizeof(CheckpointerRequest));
 
            for (i = 0; i < n; i++)
            {
                requests[i] = CheckpointerShmem->requests[CheckpointerShmem->head];
                CheckpointerShmem->head = (CheckpointerShmem->head + 1) % CheckpointerShmem->max_requests;
            }
 
            CheckpointerShmem->num_requests -= n;
 
        }
 
        START_CRIT_SECTION();
 
        /* Are there any requests in the queue? If so, keep going. */
        loop = CheckpointerShmem->num_requests != 0;
 
        LWLockRelease(CheckpointerCommLock);
 
        for (request = requests; n > 0; request++, n--)
            RememberSyncRequest(&request->ftag, request->type);
 
        END_CRIT_SECTION();
    } while (loop);
 
    if (requests)
        pfree(requests);
}

References AmCheckpointerProcess, CheckpointerShmem, CKPT_REQ_BATCH_SIZE, END_CRIT_SECTION, CheckpointerRequest::ftag, CheckpointerShmemStruct::head, i, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), CheckpointerShmemStruct::max_requests, Min, CheckpointerShmemStruct::num_requests, palloc(), pfree(), RememberSyncRequest(), CheckpointerShmemStruct::requests, START_CRIT_SECTION, and CheckpointerRequest::type.

Referenced by CheckpointerMain(), CheckpointWriteDelay(), CreateCheckPoint(), ProcessSyncRequests(), SyncPostCheckpoint(), and SyncPreCheckpoint().

CheckArchiveTimeout()

static void CheckArchiveTimeout ( void  )

static

Definition at line 703 of file checkpointer.c.

{
    pg_time_t   now;
    pg_time_t   last_time;
    XLogRecPtr  last_switch_lsn;
 
    if (XLogArchiveTimeout <= 0 || RecoveryInProgress())
        return;
 
    now = (pg_time_t) time(NULL);
 
    /* First we do a quick check using possibly-stale local state. */
    if ((int) (now - last_xlog_switch_time) < XLogArchiveTimeout)
        return;
 
    /*
     * Update local state ... note that last_xlog_switch_time is the last time
     * a switch was performed *or requested*.
     */
    last_time = GetLastSegSwitchData(&last_switch_lsn);
 
    last_xlog_switch_time = Max(last_xlog_switch_time, last_time);
 
    /* Now we can do the real checks */
    if ((int) (now - last_xlog_switch_time) >= XLogArchiveTimeout)
    {
        /*
         * Switch segment only when "important" WAL has been logged since the
         * last segment switch (last_switch_lsn points to end of segment
         * switch occurred in).
         */
        if (GetLastImportantRecPtr() > last_switch_lsn)
        {
            XLogRecPtr  switchpoint;
 
            /* mark switch as unimportant, avoids triggering checkpoints */
            switchpoint = RequestXLogSwitch(true);
 
            /*
             * If the returned pointer points exactly to a segment boundary,
             * assume nothing happened.
             */
            if (XLogSegmentOffset(switchpoint, wal_segment_size) != 0)
                elog(DEBUG1, "write-ahead log switch forced (\"archive_timeout\"=%d)",
                     XLogArchiveTimeout);
        }
 
        /*
         * Update state in any case, so we don't retry constantly when the
         * system is idle.
         */
        last_xlog_switch_time = now;
    }
}

References DEBUG1, elog, GetLastImportantRecPtr(), GetLastSegSwitchData(), last_xlog_switch_time, Max, now(), RecoveryInProgress(), RequestXLogSwitch(), wal_segment_size, XLogArchiveTimeout, and XLogSegmentOffset.

Referenced by CheckpointerMain(), and CheckpointWriteDelay().

CheckpointerMain()

void CheckpointerMain	(	const void *	startup_data,
		size_t	startup_data_len
	)

Definition at line 195 of file checkpointer.c.

{
    sigjmp_buf  local_sigjmp_buf;
    MemoryContext checkpointer_context;
 
    Assert(startup_data_len == 0);
 
    MyBackendType = B_CHECKPOINTER;
    AuxiliaryProcessMainCommon();
 
    CheckpointerShmem->checkpointer_pid = MyProcPid;
 
    /*
     * Properly accept or ignore signals the postmaster might send us
     *
     * Note: we deliberately ignore SIGTERM, because during a standard Unix
     * system shutdown cycle, init will SIGTERM all processes at once.  We
     * want to wait for the backends to exit, whereupon the postmaster will
     * tell us it's okay to shut down (via SIGUSR2).
     */
    pqsignal(SIGHUP, SignalHandlerForConfigReload);
    pqsignal(SIGINT, ReqShutdownXLOG);
    pqsignal(SIGTERM, SIG_IGN); /* ignore SIGTERM */
    /* SIGQUIT handler was already set up by InitPostmasterChild */
    pqsignal(SIGALRM, SIG_IGN);
    pqsignal(SIGPIPE, SIG_IGN);
    pqsignal(SIGUSR1, procsignal_sigusr1_handler);
    pqsignal(SIGUSR2, SignalHandlerForShutdownRequest);
 
    /*
     * Reset some signals that are accepted by postmaster but not here
     */
    pqsignal(SIGCHLD, SIG_DFL);
 
    /*
     * Initialize so that first time-driven event happens at the correct time.
     */
    last_checkpoint_time = last_xlog_switch_time = (pg_time_t) time(NULL);
 
    /*
     * Write out stats after shutdown. This needs to be called by exactly one
     * process during a normal shutdown, and since checkpointer is shut down
     * very late...
     *
     * While e.g. walsenders are active after the shutdown checkpoint has been
     * written (and thus could produce more stats), checkpointer stays around
     * after the shutdown checkpoint has been written. postmaster will only
     * signal checkpointer to exit after all processes that could emit stats
     * have been shut down.
     */
    before_shmem_exit(pgstat_before_server_shutdown, 0);
 
    /*
     * Create a memory context that we will do all our work in.  We do this so
     * that we can reset the context during error recovery and thereby avoid
     * possible memory leaks.  Formerly this code just ran in
     * TopMemoryContext, but resetting that would be a really bad idea.
     */
    checkpointer_context = AllocSetContextCreate(TopMemoryContext,
                                                 "Checkpointer",
                                                 ALLOCSET_DEFAULT_SIZES);
    MemoryContextSwitchTo(checkpointer_context);
 
    /*
     * If an exception is encountered, processing resumes here.
     *
     * You might wonder why this isn't coded as an infinite loop around a
     * PG_TRY construct.  The reason is that this is the bottom of the
     * exception stack, and so with PG_TRY there would be no exception handler
     * in force at all during the CATCH part.  By leaving the outermost setjmp
     * always active, we have at least some chance of recovering from an error
     * during error recovery.  (If we get into an infinite loop thereby, it
     * will soon be stopped by overflow of elog.c's internal state stack.)
     *
     * Note that we use sigsetjmp(..., 1), so that the prevailing signal mask
     * (to wit, BlockSig) will be restored when longjmp'ing to here.  Thus,
     * signals other than SIGQUIT will be blocked until we complete error
     * recovery.  It might seem that this policy makes the HOLD_INTERRUPTS()
     * call redundant, but it is not since InterruptPending might be set
     * already.
     */
    if (sigsetjmp(local_sigjmp_buf, 1) != 0)
    {
        /* Since not using PG_TRY, must reset error stack by hand */
        error_context_stack = NULL;
 
        /* Prevent interrupts while cleaning up */
        HOLD_INTERRUPTS();
 
        /* Report the error to the server log */
        EmitErrorReport();
 
        /*
         * These operations are really just a minimal subset of
         * AbortTransaction().  We don't have very many resources to worry
         * about in checkpointer, but we do have LWLocks, buffers, and temp
         * files.
         */
        LWLockReleaseAll();
        ConditionVariableCancelSleep();
        pgstat_report_wait_end();
        pgaio_error_cleanup();
        UnlockBuffers();
        ReleaseAuxProcessResources(false);
        AtEOXact_Buffers(false);
        AtEOXact_SMgr();
        AtEOXact_Files(false);
        AtEOXact_HashTables(false);
 
        /* Warn any waiting backends that the checkpoint failed. */
        if (ckpt_active)
        {
            SpinLockAcquire(&CheckpointerShmem->ckpt_lck);
            CheckpointerShmem->ckpt_failed++;
            CheckpointerShmem->ckpt_done = CheckpointerShmem->ckpt_started;
            SpinLockRelease(&CheckpointerShmem->ckpt_lck);
 
            ConditionVariableBroadcast(&CheckpointerShmem->done_cv);
 
            ckpt_active = false;
        }
 
        /*
         * Now return to normal top-level context and clear ErrorContext for
         * next time.
         */
        MemoryContextSwitchTo(checkpointer_context);
        FlushErrorState();
 
        /* Flush any leaked data in the top-level context */
        MemoryContextReset(checkpointer_context);
 
        /* Now we can allow interrupts again */
        RESUME_INTERRUPTS();
 
        /*
         * Sleep at least 1 second after any error.  A write error is likely
         * to be repeated, and we don't want to be filling the error logs as
         * fast as we can.
         */
        pg_usleep(1000000L);
    }
 
    /* We can now handle ereport(ERROR) */
    PG_exception_stack = &local_sigjmp_buf;
 
    /*
     * Unblock signals (they were blocked when the postmaster forked us)
     */
    sigprocmask(SIG_SETMASK, &UnBlockSig, NULL);
 
    /*
     * Ensure all shared memory values are set correctly for the config. Doing
     * this here ensures no race conditions from other concurrent updaters.
     */
    UpdateSharedMemoryConfig();
 
    /*
     * Advertise our proc number that backends can use to wake us up while
     * we're sleeping.
     */
    ProcGlobal->checkpointerProc = MyProcNumber;
 
    /*
     * Loop until we've been asked to write the shutdown checkpoint or
     * terminate.
     */
    for (;;)
    {
        bool        do_checkpoint = false;
        int         flags = 0;
        pg_time_t   now;
        int         elapsed_secs;
        int         cur_timeout;
        bool        chkpt_or_rstpt_requested = false;
        bool        chkpt_or_rstpt_timed = false;
 
        /* Clear any already-pending wakeups */
        ResetLatch(MyLatch);
 
        /*
         * Process any requests or signals received recently.
         */
        AbsorbSyncRequests();
 
        ProcessCheckpointerInterrupts();
        if (ShutdownXLOGPending || ShutdownRequestPending)
            break;
 
        /*
         * Detect a pending checkpoint request by checking whether the flags
         * word in shared memory is nonzero.  We shouldn't need to acquire the
         * ckpt_lck for this.
         */
        if (((volatile CheckpointerShmemStruct *) CheckpointerShmem)->ckpt_flags)
        {
            do_checkpoint = true;
            chkpt_or_rstpt_requested = true;
        }
 
        /*
         * Force a checkpoint if too much time has elapsed since the last one.
         * Note that we count a timed checkpoint in stats only when this
         * occurs without an external request, but we set the CAUSE_TIME flag
         * bit even if there is also an external request.
         */
        now = (pg_time_t) time(NULL);
        elapsed_secs = now - last_checkpoint_time;
        if (elapsed_secs >= CheckPointTimeout)
        {
            if (!do_checkpoint)
                chkpt_or_rstpt_timed = true;
            do_checkpoint = true;
            flags |= CHECKPOINT_CAUSE_TIME;
        }
 
        /*
         * Do a checkpoint if requested.
         */
        if (do_checkpoint)
        {
            bool        ckpt_performed = false;
            bool        do_restartpoint;
 
            /* Check if we should perform a checkpoint or a restartpoint. */
            do_restartpoint = RecoveryInProgress();
 
            /*
             * Atomically fetch the request flags to figure out what kind of a
             * checkpoint we should perform, and increase the started-counter
             * to acknowledge that we've started a new checkpoint.
             */
            SpinLockAcquire(&CheckpointerShmem->ckpt_lck);
            flags |= CheckpointerShmem->ckpt_flags;
            CheckpointerShmem->ckpt_flags = 0;
            CheckpointerShmem->ckpt_started++;
            SpinLockRelease(&CheckpointerShmem->ckpt_lck);
 
            ConditionVariableBroadcast(&CheckpointerShmem->start_cv);
 
            /*
             * The end-of-recovery checkpoint is a real checkpoint that's
             * performed while we're still in recovery.
             */
            if (flags & CHECKPOINT_END_OF_RECOVERY)
                do_restartpoint = false;
 
            if (chkpt_or_rstpt_timed)
            {
                chkpt_or_rstpt_timed = false;
                if (do_restartpoint)
                    PendingCheckpointerStats.restartpoints_timed++;
                else
                    PendingCheckpointerStats.num_timed++;
            }
 
            if (chkpt_or_rstpt_requested)
            {
                chkpt_or_rstpt_requested = false;
                if (do_restartpoint)
                    PendingCheckpointerStats.restartpoints_requested++;
                else
                    PendingCheckpointerStats.num_requested++;
            }
 
            /*
             * We will warn if (a) too soon since last checkpoint (whatever
             * caused it) and (b) somebody set the CHECKPOINT_CAUSE_XLOG flag
             * since the last checkpoint start.  Note in particular that this
             * implementation will not generate warnings caused by
             * CheckPointTimeout < CheckPointWarning.
             */
            if (!do_restartpoint &&
                (flags & CHECKPOINT_CAUSE_XLOG) &&
                elapsed_secs < CheckPointWarning)
                ereport(LOG,
                        (errmsg_plural("checkpoints are occurring too frequently (%d second apart)",
                                       "checkpoints are occurring too frequently (%d seconds apart)",
                                       elapsed_secs,
                                       elapsed_secs),
                         errhint("Consider increasing the configuration parameter \"%s\".", "max_wal_size")));
 
            /*
             * Initialize checkpointer-private variables used during
             * checkpoint.
             */
            ckpt_active = true;
            if (do_restartpoint)
                ckpt_start_recptr = GetXLogReplayRecPtr(NULL);
            else
                ckpt_start_recptr = GetInsertRecPtr();
            ckpt_start_time = now;
            ckpt_cached_elapsed = 0;
 
            /*
             * Do the checkpoint.
             */
            if (!do_restartpoint)
                ckpt_performed = CreateCheckPoint(flags);
            else
                ckpt_performed = CreateRestartPoint(flags);
 
            /*
             * After any checkpoint, free all smgr objects.  Otherwise we
             * would never do so for dropped relations, as the checkpointer
             * does not process shared invalidation messages or call
             * AtEOXact_SMgr().
             */
            smgrdestroyall();
 
            /*
             * Indicate checkpoint completion to any waiting backends.
             */
            SpinLockAcquire(&CheckpointerShmem->ckpt_lck);
            CheckpointerShmem->ckpt_done = CheckpointerShmem->ckpt_started;
            SpinLockRelease(&CheckpointerShmem->ckpt_lck);
 
            ConditionVariableBroadcast(&CheckpointerShmem->done_cv);
 
            if (!do_restartpoint)
            {
                /*
                 * Note we record the checkpoint start time not end time as
                 * last_checkpoint_time.  This is so that time-driven
                 * checkpoints happen at a predictable spacing.
                 */
                last_checkpoint_time = now;
 
                if (ckpt_performed)
                    PendingCheckpointerStats.num_performed++;
            }
            else
            {
                if (ckpt_performed)
                {
                    /*
                     * The same as for checkpoint. Please see the
                     * corresponding comment.
                     */
                    last_checkpoint_time = now;
 
                    PendingCheckpointerStats.restartpoints_performed++;
                }
                else
                {
                    /*
                     * We were not able to perform the restartpoint
                     * (checkpoints throw an ERROR in case of error).  Most
                     * likely because we have not received any new checkpoint
                     * WAL records since the last restartpoint. Try again in
                     * 15 s.
                     */
                    last_checkpoint_time = now - CheckPointTimeout + 15;
                }
            }
 
            ckpt_active = false;
 
            /*
             * We may have received an interrupt during the checkpoint and the
             * latch might have been reset (e.g. in CheckpointWriteDelay).
             */
            ProcessCheckpointerInterrupts();
            if (ShutdownXLOGPending || ShutdownRequestPending)
                break;
        }
 
        /*
         * Disable logical decoding if someone requested it. See comments atop
         * logicalctl.c.
         */
        DisableLogicalDecodingIfNecessary();
 
        /* Check for archive_timeout and switch xlog files if necessary. */
        CheckArchiveTimeout();
 
        /* Report pending statistics to the cumulative stats system */
        pgstat_report_checkpointer();
        pgstat_report_wal(true);
 
        /*
         * If any checkpoint flags have been set, redo the loop to handle the
         * checkpoint without sleeping.
         */
        if (((volatile CheckpointerShmemStruct *) CheckpointerShmem)->ckpt_flags)
            continue;
 
        /*
         * Sleep until we are signaled or it's time for another checkpoint or
         * xlog file switch.
         */
        now = (pg_time_t) time(NULL);
        elapsed_secs = now - last_checkpoint_time;
        if (elapsed_secs >= CheckPointTimeout)
            continue;           /* no sleep for us ... */
        cur_timeout = CheckPointTimeout - elapsed_secs;
        if (XLogArchiveTimeout > 0 && !RecoveryInProgress())
        {
            elapsed_secs = now - last_xlog_switch_time;
            if (elapsed_secs >= XLogArchiveTimeout)
                continue;       /* no sleep for us ... */
            cur_timeout = Min(cur_timeout, XLogArchiveTimeout - elapsed_secs);
        }
 
        (void) WaitLatch(MyLatch,
                         WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
                         cur_timeout * 1000L /* convert to ms */ ,
                         WAIT_EVENT_CHECKPOINTER_MAIN);
    }
 
    /*
     * From here on, elog(ERROR) should end with exit(1), not send control
     * back to the sigsetjmp block above.
     */
    ExitOnAnyError = true;
 
    if (ShutdownXLOGPending)
    {
        /*
         * Close down the database.
         *
         * Since ShutdownXLOG() creates restartpoint or checkpoint, and
         * updates the statistics, increment the checkpoint request and flush
         * out pending statistic.
         */
        PendingCheckpointerStats.num_requested++;
        ShutdownXLOG(0, 0);
        pgstat_report_checkpointer();
        pgstat_report_wal(true);
 
        /*
         * Tell postmaster that we're done.
         */
        SendPostmasterSignal(PMSIGNAL_XLOG_IS_SHUTDOWN);
        ShutdownXLOGPending = false;
    }
 
    /*
     * Wait until we're asked to shut down. By separating the writing of the
     * shutdown checkpoint from checkpointer exiting, checkpointer can perform
     * some should-be-as-late-as-possible work like writing out stats.
     */
    for (;;)
    {
        /* Clear any already-pending wakeups */
        ResetLatch(MyLatch);
 
        ProcessCheckpointerInterrupts();
 
        if (ShutdownRequestPending)
            break;
 
        (void) WaitLatch(MyLatch,
                         WL_LATCH_SET | WL_EXIT_ON_PM_DEATH,
                         0,
                         WAIT_EVENT_CHECKPOINTER_SHUTDOWN);
    }
 
    /* Normal exit from the checkpointer is here */
    proc_exit(0);               /* done */
}

References AbsorbSyncRequests(), ALLOCSET_DEFAULT_SIZES, AllocSetContextCreate, Assert(), AtEOXact_Buffers(), AtEOXact_Files(), AtEOXact_HashTables(), AtEOXact_SMgr(), AuxiliaryProcessMainCommon(), B_CHECKPOINTER, before_shmem_exit(), CheckArchiveTimeout(), CHECKPOINT_CAUSE_TIME, CHECKPOINT_CAUSE_XLOG, CHECKPOINT_END_OF_RECOVERY, CheckpointerShmemStruct::checkpointer_pid, PROC_HDR::checkpointerProc, CheckpointerShmem, CheckPointTimeout, CheckPointWarning, ckpt_active, ckpt_cached_elapsed, CheckpointerShmemStruct::ckpt_done, CheckpointerShmemStruct::ckpt_failed, CheckpointerShmemStruct::ckpt_flags, CheckpointerShmemStruct::ckpt_lck, ckpt_start_recptr, ckpt_start_time, CheckpointerShmemStruct::ckpt_started, ConditionVariableBroadcast(), ConditionVariableCancelSleep(), CreateCheckPoint(), CreateRestartPoint(), DisableLogicalDecodingIfNecessary(), CheckpointerShmemStruct::done_cv, EmitErrorReport(), ereport, errhint(), errmsg_plural(), error_context_stack, ExitOnAnyError, FlushErrorState(), GetInsertRecPtr(), GetXLogReplayRecPtr(), HOLD_INTERRUPTS, last_checkpoint_time, last_xlog_switch_time, LOG, LWLockReleaseAll(), MemoryContextReset(), MemoryContextSwitchTo(), Min, MyBackendType, MyLatch, MyProcNumber, MyProcPid, now(), PgStat_CheckpointerStats::num_performed, PgStat_CheckpointerStats::num_requested, PgStat_CheckpointerStats::num_timed, PendingCheckpointerStats, PG_exception_stack, pg_usleep(), pgaio_error_cleanup(), pgstat_before_server_shutdown(), pgstat_report_checkpointer(), pgstat_report_wait_end(), pgstat_report_wal(), PMSIGNAL_XLOG_IS_SHUTDOWN, pqsignal, proc_exit(), ProcessCheckpointerInterrupts(), ProcGlobal, procsignal_sigusr1_handler(), RecoveryInProgress(), ReleaseAuxProcessResources(), ReqShutdownXLOG(), ResetLatch(), PgStat_CheckpointerStats::restartpoints_performed, PgStat_CheckpointerStats::restartpoints_requested, PgStat_CheckpointerStats::restartpoints_timed, RESUME_INTERRUPTS, SendPostmasterSignal(), ShutdownRequestPending, ShutdownXLOG(), ShutdownXLOGPending, SIGALRM, SIGCHLD, SIGHUP, SignalHandlerForConfigReload(), SignalHandlerForShutdownRequest(), SIGPIPE, SIGUSR1, SIGUSR2, smgrdestroyall(), SpinLockAcquire, SpinLockRelease, CheckpointerShmemStruct::start_cv, TopMemoryContext, UnBlockSig, UnlockBuffers(), UpdateSharedMemoryConfig(), WaitLatch(), WL_EXIT_ON_PM_DEATH, WL_LATCH_SET, WL_TIMEOUT, and XLogArchiveTimeout.

CheckpointerShmemInit()

void CheckpointerShmemInit

(

void

)

Definition at line 979 of file checkpointer.c.

{
    Size        size = CheckpointerShmemSize();
    bool        found;
 
    CheckpointerShmem = (CheckpointerShmemStruct *)
        ShmemInitStruct("Checkpointer Data",
                        size,
                        &found);
 
    if (!found)
    {
        /*
         * First time through, so initialize.  Note that we zero the whole
         * requests array; this is so that CompactCheckpointerRequestQueue can
         * assume that any pad bytes in the request structs are zeroes.
         */
        MemSet(CheckpointerShmem, 0, size);
        SpinLockInit(&CheckpointerShmem->ckpt_lck);
        CheckpointerShmem->max_requests = Min(NBuffers, MAX_CHECKPOINT_REQUESTS);
        CheckpointerShmem->head = CheckpointerShmem->tail = 0;
        ConditionVariableInit(&CheckpointerShmem->start_cv);
        ConditionVariableInit(&CheckpointerShmem->done_cv);
    }
}

References CheckpointerShmem, CheckpointerShmemSize(), CheckpointerShmemStruct::ckpt_lck, ConditionVariableInit(), CheckpointerShmemStruct::done_cv, CheckpointerShmemStruct::head, MAX_CHECKPOINT_REQUESTS, CheckpointerShmemStruct::max_requests, MemSet, Min, NBuffers, ShmemInitStruct(), SpinLockInit, CheckpointerShmemStruct::start_cv, and CheckpointerShmemStruct::tail.

Referenced by CreateOrAttachShmemStructs().

CheckpointerShmemSize()

Size CheckpointerShmemSize

(

void

)

Definition at line 957 of file checkpointer.c.

{
    Size        size;
 
    /*
     * The size of the requests[] array is arbitrarily set equal to NBuffers.
     * But there is a cap of MAX_CHECKPOINT_REQUESTS to prevent accumulating
     * too many checkpoint requests in the ring buffer.
     */
    size = offsetof(CheckpointerShmemStruct, requests);
    size = add_size(size, mul_size(Min(NBuffers,
                                       MAX_CHECKPOINT_REQUESTS),
                                   sizeof(CheckpointerRequest)));
 
    return size;
}

References add_size(), MAX_CHECKPOINT_REQUESTS, Min, mul_size(), and NBuffers.

Referenced by CalculateShmemSize(), and CheckpointerShmemInit().

CheckpointWriteDelay()

void CheckpointWriteDelay	(	int	flags,
		double	progress
	)

Definition at line 791 of file checkpointer.c.

{
    static int  absorb_counter = WRITES_PER_ABSORB;
 
    /* Do nothing if checkpoint is being executed by non-checkpointer process */
    if (!AmCheckpointerProcess())
        return;
 
    /*
     * Perform the usual duties and take a nap, unless we're behind schedule,
     * in which case we just try to catch up as quickly as possible.
     */
    if (!(flags & CHECKPOINT_FAST) &&
        !ShutdownXLOGPending &&
        !ShutdownRequestPending &&
        !FastCheckpointRequested() &&
        IsCheckpointOnSchedule(progress))
    {
        if (ConfigReloadPending)
        {
            ConfigReloadPending = false;
            ProcessConfigFile(PGC_SIGHUP);
            /* update shmem copies of config variables */
            UpdateSharedMemoryConfig();
        }
 
        AbsorbSyncRequests();
        absorb_counter = WRITES_PER_ABSORB;
 
        CheckArchiveTimeout();
 
        /* Report interim statistics to the cumulative stats system */
        pgstat_report_checkpointer();
 
        /*
         * This sleep used to be connected to bgwriter_delay, typically 200ms.
         * That resulted in more frequent wakeups if not much work to do.
         * Checkpointer and bgwriter are no longer related so take the Big
         * Sleep.
         */
        WaitLatch(MyLatch, WL_LATCH_SET | WL_EXIT_ON_PM_DEATH | WL_TIMEOUT,
                  100,
                  WAIT_EVENT_CHECKPOINT_WRITE_DELAY);
        ResetLatch(MyLatch);
    }
    else if (--absorb_counter <= 0)
    {
        /*
         * Absorb pending fsync requests after each WRITES_PER_ABSORB write
         * operations even when we don't sleep, to prevent overflow of the
         * fsync request queue.
         */
        AbsorbSyncRequests();
        absorb_counter = WRITES_PER_ABSORB;
    }
 
    /* Check for barrier events. */
    if (ProcSignalBarrierPending)
        ProcessProcSignalBarrier();
}

References AbsorbSyncRequests(), AmCheckpointerProcess, CheckArchiveTimeout(), CHECKPOINT_FAST, ConfigReloadPending, FastCheckpointRequested(), IsCheckpointOnSchedule(), MyLatch, PGC_SIGHUP, pgstat_report_checkpointer(), ProcessConfigFile(), ProcessProcSignalBarrier(), ProcSignalBarrierPending, progress, ResetLatch(), ShutdownRequestPending, ShutdownXLOGPending, UpdateSharedMemoryConfig(), WaitLatch(), WL_EXIT_ON_PM_DEATH, WL_LATCH_SET, WL_TIMEOUT, and WRITES_PER_ABSORB.

Referenced by BufferSync().

CompactCheckpointerRequestQueue()

static bool CompactCheckpointerRequestQueue ( void  )

static

Definition at line 1297 of file checkpointer.c.

{
    struct CheckpointerSlotMapping
    {
        CheckpointerRequest request;
        int         ring_idx;
    };
 
    int         n;
    int         num_skipped = 0;
    int         head;
    int         max_requests;
    int         num_requests;
    int         read_idx,
                write_idx;
    HASHCTL     ctl;
    HTAB       *htab;
    bool       *skip_slot;
 
    /* must hold CheckpointerCommLock in exclusive mode */
    Assert(LWLockHeldByMe(CheckpointerCommLock));
 
    /* Avoid memory allocations in a critical section. */
    if (CritSectionCount > 0)
        return false;
 
    max_requests = CheckpointerShmem->max_requests;
    num_requests = CheckpointerShmem->num_requests;
 
    /* Initialize skip_slot array */
    skip_slot = palloc0_array(bool, max_requests);
 
    head = CheckpointerShmem->head;
 
    /* Initialize temporary hash table */
    ctl.keysize = sizeof(CheckpointerRequest);
    ctl.entrysize = sizeof(struct CheckpointerSlotMapping);
    ctl.hcxt = CurrentMemoryContext;
 
    htab = hash_create("CompactCheckpointerRequestQueue",
                       CheckpointerShmem->num_requests,
                       &ctl,
                       HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
 
    /*
     * The basic idea here is that a request can be skipped if it's followed
     * by a later, identical request.  It might seem more sensible to work
     * backwards from the end of the queue and check whether a request is
     * *preceded* by an earlier, identical request, in the hopes of doing less
     * copying.  But that might change the semantics, if there's an
     * intervening SYNC_FORGET_REQUEST or SYNC_FILTER_REQUEST, so we do it
     * this way.  It would be possible to be even smarter if we made the code
     * below understand the specific semantics of such requests (it could blow
     * away preceding entries that would end up being canceled anyhow), but
     * it's not clear that the extra complexity would buy us anything.
     */
    read_idx = head;
    for (n = 0; n < num_requests; n++)
    {
        CheckpointerRequest *request;
        struct CheckpointerSlotMapping *slotmap;
        bool        found;
 
        /*
         * We use the request struct directly as a hashtable key.  This
         * assumes that any padding bytes in the structs are consistently the
         * same, which should be okay because we zeroed them in
         * CheckpointerShmemInit.  Note also that RelFileLocator had better
         * contain no pad bytes.
         */
        request = &CheckpointerShmem->requests[read_idx];
        slotmap = hash_search(htab, request, HASH_ENTER, &found);
        if (found)
        {
            /* Duplicate, so mark the previous occurrence as skippable */
            skip_slot[slotmap->ring_idx] = true;
            num_skipped++;
        }
        /* Remember slot containing latest occurrence of this request value */
        slotmap->ring_idx = read_idx;
 
        /* Move to the next request in the ring buffer */
        read_idx = (read_idx + 1) % max_requests;
    }
 
    /* Done with the hash table. */
    hash_destroy(htab);
 
    /* If no duplicates, we're out of luck. */
    if (!num_skipped)
    {
        pfree(skip_slot);
        return false;
    }
 
    /* We found some duplicates; remove them. */
    read_idx = write_idx = head;
    for (n = 0; n < num_requests; n++)
    {
        /* If this slot is NOT skipped, keep it */
        if (!skip_slot[read_idx])
        {
            /* If the read and write positions are different, copy the request */
            if (write_idx != read_idx)
                CheckpointerShmem->requests[write_idx] =
                    CheckpointerShmem->requests[read_idx];
 
            /* Advance the write position */
            write_idx = (write_idx + 1) % max_requests;
        }
 
        read_idx = (read_idx + 1) % max_requests;
    }
 
    /*
     * Update ring buffer state: head remains the same, tail moves, count
     * decreases
     */
    CheckpointerShmem->tail = write_idx;
    CheckpointerShmem->num_requests -= num_skipped;
 
    ereport(DEBUG1,
            (errmsg_internal("compacted fsync request queue from %d entries to %d entries",
                             num_requests, CheckpointerShmem->num_requests)));
 
    /* Cleanup. */
    pfree(skip_slot);
    return true;
}

References Assert(), CheckpointerShmem, CritSectionCount, ctl, CurrentMemoryContext, DEBUG1, ereport, errmsg_internal(), HASH_BLOBS, HASH_CONTEXT, hash_create(), hash_destroy(), HASH_ELEM, HASH_ENTER, hash_search(), CheckpointerShmemStruct::head, LWLockHeldByMe(), CheckpointerShmemStruct::max_requests, CheckpointerShmemStruct::num_requests, palloc0_array, pfree(), CheckpointerShmemStruct::requests, and CheckpointerShmemStruct::tail.

Referenced by ForwardSyncRequest().

ExecCheckpoint()

void ExecCheckpoint	(	ParseState *	pstate,
		CheckPointStmt *	stmt
	)

Definition at line 1012 of file checkpointer.c.

{
    bool        fast = true;
    bool        unlogged = false;
 
    foreach_ptr(DefElem, opt, stmt->options)
    {
        if (strcmp(opt->defname, "mode") == 0)
        {
            char       *mode = defGetString(opt);
 
            if (strcmp(mode, "spread") == 0)
                fast = false;
            else if (strcmp(mode, "fast") != 0)
                ereport(ERROR,
                        (errcode(ERRCODE_SYNTAX_ERROR),
                         errmsg("unrecognized value for %s option \"%s\": \"%s\"",
                                "CHECKPOINT", "mode", mode),
                         parser_errposition(pstate, opt->location)));
        }
        else if (strcmp(opt->defname, "flush_unlogged") == 0)
            unlogged = defGetBoolean(opt);
        else
            ereport(ERROR,
                    (errcode(ERRCODE_SYNTAX_ERROR),
                     errmsg("unrecognized %s option \"%s\"",
                            "CHECKPOINT", opt->defname),
                     parser_errposition(pstate, opt->location)));
    }
 
    if (!has_privs_of_role(GetUserId(), ROLE_PG_CHECKPOINT))
        ereport(ERROR,
                (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
        /* translator: %s is name of an SQL command (e.g., CHECKPOINT) */
                 errmsg("permission denied to execute %s command",
                        "CHECKPOINT"),
                 errdetail("Only roles with privileges of the \"%s\" role may execute this command.",
                           "pg_checkpoint")));
 
    RequestCheckpoint(CHECKPOINT_WAIT |
                      (fast ? CHECKPOINT_FAST : 0) |
                      (unlogged ? CHECKPOINT_FLUSH_UNLOGGED : 0) |
                      (RecoveryInProgress() ? 0 : CHECKPOINT_FORCE));
}

References CHECKPOINT_FAST, CHECKPOINT_FLUSH_UNLOGGED, CHECKPOINT_FORCE, CHECKPOINT_WAIT, defGetBoolean(), defGetString(), ereport, errcode(), errdetail(), errmsg(), ERROR, foreach_ptr, GetUserId(), has_privs_of_role(), mode, parser_errposition(), RecoveryInProgress(), RequestCheckpoint(), and stmt.

Referenced by standard_ProcessUtility().

FastCheckpointRequested()

static bool FastCheckpointRequested ( void  )

static

Definition at line 764 of file checkpointer.c.

{
    volatile CheckpointerShmemStruct *cps = CheckpointerShmem;
 
    /*
     * We don't need to acquire the ckpt_lck in this case because we're only
     * looking at a single flag bit.
     */
    if (cps->ckpt_flags & CHECKPOINT_FAST)
        return true;
    return false;
}

References CHECKPOINT_FAST, CheckpointerShmem, and CheckpointerShmemStruct::ckpt_flags.

Referenced by CheckpointWriteDelay().

FirstCallSinceLastCheckpoint()

bool FirstCallSinceLastCheckpoint

(

void

)

Definition at line 1527 of file checkpointer.c.

{
    static int  ckpt_done = 0;
    int         new_done;
    bool        FirstCall = false;
 
    SpinLockAcquire(&CheckpointerShmem->ckpt_lck);
    new_done = CheckpointerShmem->ckpt_done;
    SpinLockRelease(&CheckpointerShmem->ckpt_lck);
 
    if (new_done != ckpt_done)
        FirstCall = true;
 
    ckpt_done = new_done;
 
    return FirstCall;
}

References CheckpointerShmem, CheckpointerShmemStruct::ckpt_done, CheckpointerShmemStruct::ckpt_lck, SpinLockAcquire, and SpinLockRelease.

Referenced by BackgroundWriterMain().

ForwardSyncRequest()

bool ForwardSyncRequest	(	const FileTag *	ftag,
		SyncRequestType	type
	)

Definition at line 1225 of file checkpointer.c.

{
    CheckpointerRequest *request;
    bool        too_full;
    int         insert_pos;
 
    if (!IsUnderPostmaster)
        return false;           /* probably shouldn't even get here */
 
    if (AmCheckpointerProcess())
        elog(ERROR, "ForwardSyncRequest must not be called in checkpointer");
 
    LWLockAcquire(CheckpointerCommLock, LW_EXCLUSIVE);
 
    /*
     * If the checkpointer isn't running or the request queue is full, the
     * backend will have to perform its own fsync request.  But before forcing
     * that to happen, we can try to compact the request queue.
     */
    if (CheckpointerShmem->checkpointer_pid == 0 ||
        (CheckpointerShmem->num_requests >= CheckpointerShmem->max_requests &&
         !CompactCheckpointerRequestQueue()))
    {
        LWLockRelease(CheckpointerCommLock);
        return false;
    }
 
    /* OK, insert request */
    insert_pos = CheckpointerShmem->tail;
    request = &CheckpointerShmem->requests[insert_pos];
    request->ftag = *ftag;
    request->type = type;
 
    CheckpointerShmem->tail = (CheckpointerShmem->tail + 1) % CheckpointerShmem->max_requests;
    CheckpointerShmem->num_requests++;
 
    /* If queue is more than half full, nudge the checkpointer to empty it */
    too_full = (CheckpointerShmem->num_requests >=
                CheckpointerShmem->max_requests / 2);
 
    LWLockRelease(CheckpointerCommLock);
 
    /* ... but not till after we release the lock */
    if (too_full)
    {
        volatile PROC_HDR *procglobal = ProcGlobal;
        ProcNumber  checkpointerProc = procglobal->checkpointerProc;
 
        if (checkpointerProc != INVALID_PROC_NUMBER)
            SetLatch(&GetPGProcByNumber(checkpointerProc)->procLatch);
    }
 
    return true;
}

References AmCheckpointerProcess, CheckpointerShmemStruct::checkpointer_pid, PROC_HDR::checkpointerProc, CheckpointerShmem, CompactCheckpointerRequestQueue(), elog, ERROR, CheckpointerRequest::ftag, GetPGProcByNumber, INVALID_PROC_NUMBER, IsUnderPostmaster, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), CheckpointerShmemStruct::max_requests, CheckpointerShmemStruct::num_requests, ProcGlobal, CheckpointerShmemStruct::requests, SetLatch(), CheckpointerShmemStruct::tail, CheckpointerRequest::type, and type.

Referenced by RegisterSyncRequest().

IsCheckpointOnSchedule()

static bool IsCheckpointOnSchedule ( double  progress )

static

Definition at line 861 of file checkpointer.c.

{
    XLogRecPtr  recptr;
    struct timeval now;
    double      elapsed_xlogs,
                elapsed_time;
 
    Assert(ckpt_active);
 
    /* Scale progress according to checkpoint_completion_target. */
    progress *= CheckPointCompletionTarget;
 
    /*
     * Check against the cached value first. Only do the more expensive
     * calculations once we reach the target previously calculated. Since
     * neither time or WAL insert pointer moves backwards, a freshly
     * calculated value can only be greater than or equal to the cached value.
     */
    if (progress < ckpt_cached_elapsed)
        return false;
 
    /*
     * Check progress against WAL segments written and CheckPointSegments.
     *
     * We compare the current WAL insert location against the location
     * computed before calling CreateCheckPoint. The code in XLogInsert that
     * actually triggers a checkpoint when CheckPointSegments is exceeded
     * compares against RedoRecPtr, so this is not completely accurate.
     * However, it's good enough for our purposes, we're only calculating an
     * estimate anyway.
     *
     * During recovery, we compare last replayed WAL record's location with
     * the location computed before calling CreateRestartPoint. That maintains
     * the same pacing as we have during checkpoints in normal operation, but
     * we might exceed max_wal_size by a fair amount. That's because there can
     * be a large gap between a checkpoint's redo-pointer and the checkpoint
     * record itself, and we only start the restartpoint after we've seen the
     * checkpoint record. (The gap is typically up to CheckPointSegments *
     * checkpoint_completion_target where checkpoint_completion_target is the
     * value that was in effect when the WAL was generated).
     */
    if (RecoveryInProgress())
        recptr = GetXLogReplayRecPtr(NULL);
    else
        recptr = GetInsertRecPtr();
    elapsed_xlogs = (((double) (recptr - ckpt_start_recptr)) /
                     wal_segment_size) / CheckPointSegments;
 
    if (progress < elapsed_xlogs)
    {
        ckpt_cached_elapsed = elapsed_xlogs;
        return false;
    }
 
    /*
     * Check progress against time elapsed and checkpoint_timeout.
     */
    gettimeofday(&now, NULL);
    elapsed_time = ((double) ((pg_time_t) now.tv_sec - ckpt_start_time) +
                    now.tv_usec / 1000000.0) / CheckPointTimeout;
 
    if (progress < elapsed_time)
    {
        ckpt_cached_elapsed = elapsed_time;
        return false;
    }
 
    /* It looks like we're on schedule. */
    return true;
}

References Assert(), CheckPointCompletionTarget, CheckPointSegments, CheckPointTimeout, ckpt_active, ckpt_cached_elapsed, ckpt_start_recptr, ckpt_start_time, elapsed_time(), GetInsertRecPtr(), gettimeofday(), GetXLogReplayRecPtr(), now(), progress, RecoveryInProgress(), and wal_segment_size.

Referenced by CheckpointWriteDelay().

ProcessCheckpointerInterrupts()

static void ProcessCheckpointerInterrupts ( void  )

static

Definition at line 661 of file checkpointer.c.

{
    if (ProcSignalBarrierPending)
        ProcessProcSignalBarrier();
 
    if (ConfigReloadPending)
    {
        ConfigReloadPending = false;
        ProcessConfigFile(PGC_SIGHUP);
 
        /*
         * Checkpointer is the last process to shut down, so we ask it to hold
         * the keys for a range of other tasks required most of which have
         * nothing to do with checkpointing at all.
         *
         * For various reasons, some config values can change dynamically so
         * the primary copy of them is held in shared memory to make sure all
         * backends see the same value.  We make Checkpointer responsible for
         * updating the shared memory copy if the parameter setting changes
         * because of SIGHUP.
         */
        UpdateSharedMemoryConfig();
    }
 
    /* Perform logging of memory contexts of this process */
    if (LogMemoryContextPending)
        ProcessLogMemoryContextInterrupt();
}

References ConfigReloadPending, LogMemoryContextPending, PGC_SIGHUP, ProcessConfigFile(), ProcessLogMemoryContextInterrupt(), ProcessProcSignalBarrier(), ProcSignalBarrierPending, and UpdateSharedMemoryConfig().

Referenced by CheckpointerMain().

ReqShutdownXLOG()

static void ReqShutdownXLOG ( SIGNAL_ARGS  )

static

Definition at line 940 of file checkpointer.c.

{
    ShutdownXLOGPending = true;
    SetLatch(MyLatch);
}

References MyLatch, SetLatch(), and ShutdownXLOGPending.

Referenced by CheckpointerMain().

RequestCheckpoint()

void RequestCheckpoint

(

int

flags

)

Definition at line 1075 of file checkpointer.c.

{
    int         ntries;
    int         old_failed,
                old_started;
 
    /*
     * If in a standalone backend, just do it ourselves.
     */
    if (!IsPostmasterEnvironment)
    {
        /*
         * There's no point in doing slow checkpoints in a standalone backend,
         * because there's no other backends the checkpoint could disrupt.
         */
        CreateCheckPoint(flags | CHECKPOINT_FAST);
 
        /* Free all smgr objects, as CheckpointerMain() normally would. */
        smgrdestroyall();
 
        return;
    }
 
    /*
     * Atomically set the request flags, and take a snapshot of the counters.
     * When we see ckpt_started > old_started, we know the flags we set here
     * have been seen by checkpointer.
     *
     * Note that we OR the flags with any existing flags, to avoid overriding
     * a "stronger" request by another backend.  The flag senses must be
     * chosen to make this work!
     */
    SpinLockAcquire(&CheckpointerShmem->ckpt_lck);
 
    old_failed = CheckpointerShmem->ckpt_failed;
    old_started = CheckpointerShmem->ckpt_started;
    CheckpointerShmem->ckpt_flags |= (flags | CHECKPOINT_REQUESTED);
 
    SpinLockRelease(&CheckpointerShmem->ckpt_lck);
 
    /*
     * Set checkpointer's latch to request checkpoint.  It's possible that the
     * checkpointer hasn't started yet, so we will retry a few times if
     * needed.  (Actually, more than a few times, since on slow or overloaded
     * buildfarm machines, it's been observed that the checkpointer can take
     * several seconds to start.)  However, if not told to wait for the
     * checkpoint to occur, we consider failure to set the latch to be
     * nonfatal and merely LOG it.  The checkpointer should see the request
     * when it does start, with or without the SetLatch().
     */
#define MAX_SIGNAL_TRIES 600    /* max wait 60.0 sec */
    for (ntries = 0;; ntries++)
    {
        volatile PROC_HDR *procglobal = ProcGlobal;
        ProcNumber  checkpointerProc = procglobal->checkpointerProc;
 
        if (checkpointerProc == INVALID_PROC_NUMBER)
        {
            if (ntries >= MAX_SIGNAL_TRIES || !(flags & CHECKPOINT_WAIT))
            {
                elog((flags & CHECKPOINT_WAIT) ? ERROR : LOG,
                     "could not notify checkpoint: checkpointer is not running");
                break;
            }
        }
        else
        {
            SetLatch(&GetPGProcByNumber(checkpointerProc)->procLatch);
            /* notified successfully */
            break;
        }
 
        CHECK_FOR_INTERRUPTS();
        pg_usleep(100000L);     /* wait 0.1 sec, then retry */
    }
 
    /*
     * If requested, wait for completion.  We detect completion according to
     * the algorithm given above.
     */
    if (flags & CHECKPOINT_WAIT)
    {
        int         new_started,
                    new_failed;
 
        /* Wait for a new checkpoint to start. */
        ConditionVariablePrepareToSleep(&CheckpointerShmem->start_cv);
        for (;;)
        {
            SpinLockAcquire(&CheckpointerShmem->ckpt_lck);
            new_started = CheckpointerShmem->ckpt_started;
            SpinLockRelease(&CheckpointerShmem->ckpt_lck);
 
            if (new_started != old_started)
                break;
 
            ConditionVariableSleep(&CheckpointerShmem->start_cv,
                                   WAIT_EVENT_CHECKPOINT_START);
        }
        ConditionVariableCancelSleep();
 
        /*
         * We are waiting for ckpt_done >= new_started, in a modulo sense.
         */
        ConditionVariablePrepareToSleep(&CheckpointerShmem->done_cv);
        for (;;)
        {
            int         new_done;
 
            SpinLockAcquire(&CheckpointerShmem->ckpt_lck);
            new_done = CheckpointerShmem->ckpt_done;
            new_failed = CheckpointerShmem->ckpt_failed;
            SpinLockRelease(&CheckpointerShmem->ckpt_lck);
 
            if (new_done - new_started >= 0)
                break;
 
            ConditionVariableSleep(&CheckpointerShmem->done_cv,
                                   WAIT_EVENT_CHECKPOINT_DONE);
        }
        ConditionVariableCancelSleep();
 
        if (new_failed != old_failed)
            ereport(ERROR,
                    (errmsg("checkpoint request failed"),
                     errhint("Consult recent messages in the server log for details.")));
    }
}

References CHECK_FOR_INTERRUPTS, CHECKPOINT_FAST, CHECKPOINT_REQUESTED, CHECKPOINT_WAIT, PROC_HDR::checkpointerProc, CheckpointerShmem, CheckpointerShmemStruct::ckpt_done, CheckpointerShmemStruct::ckpt_failed, CheckpointerShmemStruct::ckpt_flags, CheckpointerShmemStruct::ckpt_lck, CheckpointerShmemStruct::ckpt_started, ConditionVariableCancelSleep(), ConditionVariablePrepareToSleep(), ConditionVariableSleep(), CreateCheckPoint(), CheckpointerShmemStruct::done_cv, elog, ereport, errhint(), errmsg(), ERROR, GetPGProcByNumber, INVALID_PROC_NUMBER, IsPostmasterEnvironment, LOG, MAX_SIGNAL_TRIES, pg_usleep(), ProcGlobal, SetLatch(), smgrdestroyall(), SpinLockAcquire, SpinLockRelease, and CheckpointerShmemStruct::start_cv.

Referenced by CreateDatabaseUsingFileCopy(), do_pg_backup_start(), dropdb(), DropTableSpace(), ExecCheckpoint(), movedb(), PerformRecoveryXLogAction(), StartupXLOG(), XLogPageRead(), and XLogWrite().

UpdateSharedMemoryConfig()

static void UpdateSharedMemoryConfig ( void  )

static

Definition at line 1508 of file checkpointer.c.

{
    /* update global shmem state for sync rep */
    SyncRepUpdateSyncStandbysDefined();
 
    /*
     * If full_page_writes has been changed by SIGHUP, we update it in shared
     * memory and write an XLOG_FPW_CHANGE record.
     */
    UpdateFullPageWrites();
 
    elog(DEBUG2, "checkpointer updated shared memory configuration values");
}

References DEBUG2, elog, SyncRepUpdateSyncStandbysDefined(), and UpdateFullPageWrites().

Referenced by CheckpointerMain(), CheckpointWriteDelay(), and ProcessCheckpointerInterrupts().

WakeupCheckpointer()

void WakeupCheckpointer

(

void

)

Definition at line 1549 of file checkpointer.c.

{
    volatile PROC_HDR *procglobal = ProcGlobal;
    ProcNumber  checkpointerProc = procglobal->checkpointerProc;
 
    if (checkpointerProc != INVALID_PROC_NUMBER)
        SetLatch(&GetPGProcByNumber(checkpointerProc)->procLatch);
}

References PROC_HDR::checkpointerProc, GetPGProcByNumber, INVALID_PROC_NUMBER, ProcGlobal, and SetLatch().

Referenced by RequestDisableLogicalDecoding(), and StartupXLOG().

Variable Documentation

CheckPointCompletionTarget

double CheckPointCompletionTarget = 0.9

Definition at line 159 of file checkpointer.c.

Referenced by assign_checkpoint_completion_target(), CalculateCheckpointSegments(), IsCheckpointOnSchedule(), and XLOGfileslop().

CheckpointerShmem

CheckpointerShmemStruct* CheckpointerShmem

static

Definition at line 143 of file checkpointer.c.

Referenced by AbsorbSyncRequests(), CheckpointerMain(), CheckpointerShmemInit(), CompactCheckpointerRequestQueue(), FastCheckpointRequested(), FirstCallSinceLastCheckpoint(), ForwardSyncRequest(), and RequestCheckpoint().

CheckPointTimeout

int CheckPointTimeout = 300

Definition at line 157 of file checkpointer.c.

Referenced by CheckpointerMain(), and IsCheckpointOnSchedule().

CheckPointWarning

int CheckPointWarning = 30

Definition at line 158 of file checkpointer.c.

Referenced by CheckpointerMain().

ckpt_active

bool ckpt_active = false

static

Definition at line 164 of file checkpointer.c.

Referenced by CheckpointerMain(), and IsCheckpointOnSchedule().

ckpt_cached_elapsed

double ckpt_cached_elapsed

static

Definition at line 170 of file checkpointer.c.

Referenced by CheckpointerMain(), and IsCheckpointOnSchedule().

ckpt_start_recptr

XLogRecPtr ckpt_start_recptr

static

Definition at line 169 of file checkpointer.c.

Referenced by CheckpointerMain(), and IsCheckpointOnSchedule().

ckpt_start_time

pg_time_t ckpt_start_time

static

Definition at line 168 of file checkpointer.c.

Referenced by CheckpointerMain(), and IsCheckpointOnSchedule().

last_checkpoint_time

pg_time_t last_checkpoint_time

static

Definition at line 172 of file checkpointer.c.

Referenced by CheckpointerMain().

last_xlog_switch_time

pg_time_t last_xlog_switch_time

static

Definition at line 173 of file checkpointer.c.

Referenced by CheckArchiveTimeout(), and CheckpointerMain().

ShutdownXLOGPending

volatile sig_atomic_t ShutdownXLOGPending = false

static

Definition at line 165 of file checkpointer.c.

Referenced by CheckpointerMain(), CheckpointWriteDelay(), and ReqShutdownXLOG().