syncrep.c File Reference

#include "postgres.h"
#include <unistd.h>
#include "access/xact.h"
#include "common/int.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "replication/syncrep.h"
#include "replication/walsender.h"
#include "replication/walsender_private.h"
#include "storage/proc.h"
#include "tcop/tcopprot.h"
#include "utils/guc_hooks.h"
#include "utils/ps_status.h"

Include dependency graph for syncrep.c:

Go to the source code of this file.

Macros
#define	SyncStandbysDefined()    (SyncRepStandbyNames != NULL && SyncRepStandbyNames[0] != '\0')

Functions
static void	SyncRepQueueInsert (int mode)
static void	SyncRepCancelWait (void)
static int	SyncRepWakeQueue (bool all, int mode)
static bool	SyncRepGetSyncRecPtr (XLogRecPtr *writePtr, XLogRecPtr *flushPtr, XLogRecPtr *applyPtr, bool *am_sync)
static void	SyncRepGetOldestSyncRecPtr (XLogRecPtr *writePtr, XLogRecPtr *flushPtr, XLogRecPtr *applyPtr, SyncRepStandbyData *sync_standbys, int num_standbys)
static void	SyncRepGetNthLatestSyncRecPtr (XLogRecPtr *writePtr, XLogRecPtr *flushPtr, XLogRecPtr *applyPtr, SyncRepStandbyData *sync_standbys, int num_standbys, uint8 nth)
static int	SyncRepGetStandbyPriority (void)
static int	standby_priority_comparator (const void *a, const void *b)
static int	cmp_lsn (const void *a, const void *b)
void	SyncRepWaitForLSN (XLogRecPtr lsn, bool commit)
void	SyncRepCleanupAtProcExit (void)
void	SyncRepInitConfig (void)
void	SyncRepReleaseWaiters (void)
int	SyncRepGetCandidateStandbys (SyncRepStandbyData **standbys)
void	SyncRepUpdateSyncStandbysDefined (void)
bool	check_synchronous_standby_names (char **newval, void **extra, GucSource source)
void	assign_synchronous_standby_names (const char *newval, void *extra)
void	assign_synchronous_commit (int newval, void *extra)

Variables
char *	SyncRepStandbyNames
static bool	announce_next_takeover = true
SyncRepConfigData *	SyncRepConfig = NULL
static int	SyncRepWaitMode = SYNC_REP_NO_WAIT

Macro Definition Documentation

SyncStandbysDefined

#define SyncStandbysDefined

(

)

(SyncRepStandbyNames != NULL && SyncRepStandbyNames[0] != '\0')

Definition at line 92 of file syncrep.c.

Function Documentation

assign_synchronous_commit()

void assign_synchronous_commit	(	int	newval,
		void *	extra
	)

Definition at line 1054 of file syncrep.c.

{
    switch (newval)
    {
        case SYNCHRONOUS_COMMIT_REMOTE_WRITE:
            SyncRepWaitMode = SYNC_REP_WAIT_WRITE;
            break;
        case SYNCHRONOUS_COMMIT_REMOTE_FLUSH:
            SyncRepWaitMode = SYNC_REP_WAIT_FLUSH;
            break;
        case SYNCHRONOUS_COMMIT_REMOTE_APPLY:
            SyncRepWaitMode = SYNC_REP_WAIT_APPLY;
            break;
        default:
            SyncRepWaitMode = SYNC_REP_NO_WAIT;
            break;
    }
}

References newval, SYNC_REP_NO_WAIT, SYNC_REP_WAIT_APPLY, SYNC_REP_WAIT_FLUSH, SYNC_REP_WAIT_WRITE, SYNCHRONOUS_COMMIT_REMOTE_APPLY, SYNCHRONOUS_COMMIT_REMOTE_FLUSH, SYNCHRONOUS_COMMIT_REMOTE_WRITE, and SyncRepWaitMode.

assign_synchronous_standby_names()

void assign_synchronous_standby_names	(	const char *	newval,
		void *	extra
	)

Definition at line 1048 of file syncrep.c.

{
    SyncRepConfig = (SyncRepConfigData *) extra;
}

References SyncRepConfig.

check_synchronous_standby_names()

bool check_synchronous_standby_names	(	char **	newval,
		void **	extra,
		GucSource	source
	)

Definition at line 991 of file syncrep.c.

{
    if (*newval != NULL && (*newval)[0] != '\0')
    {
        int         parse_rc;
        SyncRepConfigData *pconf;
 
        /* Reset communication variables to ensure a fresh start */
        syncrep_parse_result = NULL;
        syncrep_parse_error_msg = NULL;
 
        /* Parse the synchronous_standby_names string */
        syncrep_scanner_init(*newval);
        parse_rc = syncrep_yyparse();
        syncrep_scanner_finish();
 
        if (parse_rc != 0 || syncrep_parse_result == NULL)
        {
            GUC_check_errcode(ERRCODE_SYNTAX_ERROR);
            if (syncrep_parse_error_msg)
                GUC_check_errdetail("%s", syncrep_parse_error_msg);
            else
                GUC_check_errdetail("synchronous_standby_names parser failed");
            return false;
        }
 
        if (syncrep_parse_result->num_sync <= 0)
        {
            GUC_check_errmsg("number of synchronous standbys (%d) must be greater than zero",
                             syncrep_parse_result->num_sync);
            return false;
        }
 
        /* GUC extra value must be guc_malloc'd, not palloc'd */
        pconf = (SyncRepConfigData *)
            guc_malloc(LOG, syncrep_parse_result->config_size);
        if (pconf == NULL)
            return false;
        memcpy(pconf, syncrep_parse_result, syncrep_parse_result->config_size);
 
        *extra = (void *) pconf;
 
        /*
         * We need not explicitly clean up syncrep_parse_result.  It, and any
         * other cruft generated during parsing, will be freed when the
         * current memory context is deleted.  (This code is generally run in
         * a short-lived context used for config file processing, so that will
         * not be very long.)
         */
    }
    else
        *extra = NULL;
 
    return true;
}

References SyncRepConfigData::config_size, GUC_check_errcode(), GUC_check_errdetail, GUC_check_errmsg, guc_malloc(), LOG, newval, SyncRepConfigData::num_sync, syncrep_parse_error_msg, syncrep_parse_result, syncrep_scanner_finish(), syncrep_scanner_init(), and syncrep_yyparse().

cmp_lsn()

static int cmp_lsn ( const void *  a, const void *  b  )

static

Definition at line 695 of file syncrep.c.

{
    XLogRecPtr  lsn1 = *((const XLogRecPtr *) a);
    XLogRecPtr  lsn2 = *((const XLogRecPtr *) b);
 
    return pg_cmp_u64(lsn2, lsn1);
}

References a, b, and pg_cmp_u64().

Referenced by SyncRepGetNthLatestSyncRecPtr().

standby_priority_comparator()

static int standby_priority_comparator ( const void *  a, const void *  b  )

static

Definition at line 790 of file syncrep.c.

{
    const SyncRepStandbyData *sa = (const SyncRepStandbyData *) a;
    const SyncRepStandbyData *sb = (const SyncRepStandbyData *) b;
 
    /* First, sort by increasing priority value */
    if (sa->sync_standby_priority != sb->sync_standby_priority)
        return sa->sync_standby_priority - sb->sync_standby_priority;
 
    /*
     * We might have equal priority values; arbitrarily break ties by position
     * in the WalSnd array.  (This is utterly bogus, since that is arrival
     * order dependent, but there are regression tests that rely on it.)
     */
    return sa->walsnd_index - sb->walsnd_index;
}

References a, b, SyncRepStandbyData::sync_standby_priority, and SyncRepStandbyData::walsnd_index.

Referenced by SyncRepGetCandidateStandbys().

SyncRepCancelWait()

static void SyncRepCancelWait ( void  )

static

Definition at line 363 of file syncrep.c.

{
    LWLockAcquire(SyncRepLock, LW_EXCLUSIVE);
    if (!dlist_node_is_detached(&MyProc->syncRepLinks))
        dlist_delete_thoroughly(&MyProc->syncRepLinks);
    MyProc->syncRepState = SYNC_REP_NOT_WAITING;
    LWLockRelease(SyncRepLock);
}

References dlist_delete_thoroughly(), dlist_node_is_detached(), LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), MyProc, SYNC_REP_NOT_WAITING, PGPROC::syncRepLinks, and PGPROC::syncRepState.

Referenced by SyncRepWaitForLSN().

SyncRepCleanupAtProcExit()

void SyncRepCleanupAtProcExit

(

void

)

Definition at line 373 of file syncrep.c.

{
    /*
     * First check if we are removed from the queue without the lock to not
     * slow down backend exit.
     */
    if (!dlist_node_is_detached(&MyProc->syncRepLinks))
    {
        LWLockAcquire(SyncRepLock, LW_EXCLUSIVE);
 
        /* maybe we have just been removed, so recheck */
        if (!dlist_node_is_detached(&MyProc->syncRepLinks))
            dlist_delete_thoroughly(&MyProc->syncRepLinks);
 
        LWLockRelease(SyncRepLock);
    }
}

References dlist_delete_thoroughly(), dlist_node_is_detached(), LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), MyProc, and PGPROC::syncRepLinks.

Referenced by ProcKill().

SyncRepGetCandidateStandbys()

int SyncRepGetCandidateStandbys

(

SyncRepStandbyData **

standbys

)

Definition at line 711 of file syncrep.c.

{
    int         i;
    int         n;
 
    /* Create result array */
    *standbys = (SyncRepStandbyData *)
        palloc(max_wal_senders * sizeof(SyncRepStandbyData));
 
    /* Quick exit if sync replication is not requested */
    if (SyncRepConfig == NULL)
        return 0;
 
    /* Collect raw data from shared memory */
    n = 0;
    for (i = 0; i < max_wal_senders; i++)
    {
        volatile WalSnd *walsnd;    /* Use volatile pointer to prevent code
                                     * rearrangement */
        SyncRepStandbyData *stby;
        WalSndState state;      /* not included in SyncRepStandbyData */
 
        walsnd = &WalSndCtl->walsnds[i];
        stby = *standbys + n;
 
        SpinLockAcquire(&walsnd->mutex);
        stby->pid = walsnd->pid;
        state = walsnd->state;
        stby->write = walsnd->write;
        stby->flush = walsnd->flush;
        stby->apply = walsnd->apply;
        stby->sync_standby_priority = walsnd->sync_standby_priority;
        SpinLockRelease(&walsnd->mutex);
 
        /* Must be active */
        if (stby->pid == 0)
            continue;
 
        /* Must be streaming or stopping */
        if (state != WALSNDSTATE_STREAMING &&
            state != WALSNDSTATE_STOPPING)
            continue;
 
        /* Must be synchronous */
        if (stby->sync_standby_priority == 0)
            continue;
 
        /* Must have a valid flush position */
        if (XLogRecPtrIsInvalid(stby->flush))
            continue;
 
        /* OK, it's a candidate */
        stby->walsnd_index = i;
        stby->is_me = (walsnd == MyWalSnd);
        n++;
    }
 
    /*
     * In quorum mode, we return all the candidates.  In priority mode, if we
     * have too many candidates then return only the num_sync ones of highest
     * priority.
     */
    if (SyncRepConfig->syncrep_method == SYNC_REP_PRIORITY &&
        n > SyncRepConfig->num_sync)
    {
        /* Sort by priority ... */
        qsort(*standbys, n, sizeof(SyncRepStandbyData),
              standby_priority_comparator);
        /* ... then report just the first num_sync ones */
        n = SyncRepConfig->num_sync;
    }
 
    return n;
}

References SyncRepStandbyData::apply, WalSnd::apply, SyncRepStandbyData::flush, WalSnd::flush, i, SyncRepStandbyData::is_me, max_wal_senders, WalSnd::mutex, MyWalSnd, SyncRepConfigData::num_sync, palloc(), SyncRepStandbyData::pid, WalSnd::pid, qsort, SpinLockAcquire, SpinLockRelease, standby_priority_comparator(), WalSnd::state, SYNC_REP_PRIORITY, SyncRepStandbyData::sync_standby_priority, WalSnd::sync_standby_priority, SyncRepConfigData::syncrep_method, SyncRepConfig, SyncRepStandbyData::walsnd_index, WalSndCtl, WalSndCtlData::walsnds, WALSNDSTATE_STOPPING, WALSNDSTATE_STREAMING, SyncRepStandbyData::write, WalSnd::write, and XLogRecPtrIsInvalid.

Referenced by pg_stat_get_wal_senders(), and SyncRepGetSyncRecPtr().

SyncRepGetNthLatestSyncRecPtr()

static void SyncRepGetNthLatestSyncRecPtr ( XLogRecPtr *  writePtr, XLogRecPtr *  flushPtr, XLogRecPtr *  applyPtr, SyncRepStandbyData *  sync_standbys, int  num_standbys, uint8  nth  )

static

Definition at line 650 of file syncrep.c.

{
    XLogRecPtr *write_array;
    XLogRecPtr *flush_array;
    XLogRecPtr *apply_array;
    int         i;
 
    /* Should have enough candidates, or somebody messed up */
    Assert(nth > 0 && nth <= num_standbys);
 
    write_array = (XLogRecPtr *) palloc(sizeof(XLogRecPtr) * num_standbys);
    flush_array = (XLogRecPtr *) palloc(sizeof(XLogRecPtr) * num_standbys);
    apply_array = (XLogRecPtr *) palloc(sizeof(XLogRecPtr) * num_standbys);
 
    for (i = 0; i < num_standbys; i++)
    {
        write_array[i] = sync_standbys[i].write;
        flush_array[i] = sync_standbys[i].flush;
        apply_array[i] = sync_standbys[i].apply;
    }
 
    /* Sort each array in descending order */
    qsort(write_array, num_standbys, sizeof(XLogRecPtr), cmp_lsn);
    qsort(flush_array, num_standbys, sizeof(XLogRecPtr), cmp_lsn);
    qsort(apply_array, num_standbys, sizeof(XLogRecPtr), cmp_lsn);
 
    /* Get Nth latest Write, Flush, Apply positions */
    *writePtr = write_array[nth - 1];
    *flushPtr = flush_array[nth - 1];
    *applyPtr = apply_array[nth - 1];
 
    pfree(write_array);
    pfree(flush_array);
    pfree(apply_array);
}

References SyncRepStandbyData::apply, Assert, cmp_lsn(), SyncRepStandbyData::flush, i, palloc(), pfree(), qsort, and SyncRepStandbyData::write.

Referenced by SyncRepGetSyncRecPtr().

SyncRepGetOldestSyncRecPtr()

static void SyncRepGetOldestSyncRecPtr ( XLogRecPtr *  writePtr, XLogRecPtr *  flushPtr, XLogRecPtr *  applyPtr, SyncRepStandbyData *  sync_standbys, int  num_standbys  )

static

Definition at line 617 of file syncrep.c.

{
    int         i;
 
    /*
     * Scan through all sync standbys and calculate the oldest Write, Flush
     * and Apply positions.  We assume *writePtr et al were initialized to
     * InvalidXLogRecPtr.
     */
    for (i = 0; i < num_standbys; i++)
    {
        XLogRecPtr  write = sync_standbys[i].write;
        XLogRecPtr  flush = sync_standbys[i].flush;
        XLogRecPtr  apply = sync_standbys[i].apply;
 
        if (XLogRecPtrIsInvalid(*writePtr) || *writePtr > write)
            *writePtr = write;
        if (XLogRecPtrIsInvalid(*flushPtr) || *flushPtr > flush)
            *flushPtr = flush;
        if (XLogRecPtrIsInvalid(*applyPtr) || *applyPtr > apply)
            *applyPtr = apply;
    }
}

References SyncRepStandbyData::apply, SyncRepStandbyData::flush, i, SyncRepStandbyData::write, write, and XLogRecPtrIsInvalid.

Referenced by SyncRepGetSyncRecPtr().

SyncRepGetStandbyPriority()

static int SyncRepGetStandbyPriority ( void  )

static

Definition at line 817 of file syncrep.c.

{
    const char *standby_name;
    int         priority;
    bool        found = false;
 
    /*
     * Since synchronous cascade replication is not allowed, we always set the
     * priority of cascading walsender to zero.
     */
    if (am_cascading_walsender)
        return 0;
 
    if (!SyncStandbysDefined() || SyncRepConfig == NULL)
        return 0;
 
    standby_name = SyncRepConfig->member_names;
    for (priority = 1; priority <= SyncRepConfig->nmembers; priority++)
    {
        if (pg_strcasecmp(standby_name, application_name) == 0 ||
            strcmp(standby_name, "*") == 0)
        {
            found = true;
            break;
        }
        standby_name += strlen(standby_name) + 1;
    }
 
    if (!found)
        return 0;
 
    /*
     * In quorum-based sync replication, all the standbys in the list have the
     * same priority, one.
     */
    return (SyncRepConfig->syncrep_method == SYNC_REP_PRIORITY) ? priority : 1;
}

References am_cascading_walsender, application_name, SyncRepConfigData::member_names, SyncRepConfigData::nmembers, pg_strcasecmp(), SYNC_REP_PRIORITY, SyncRepConfigData::syncrep_method, SyncRepConfig, and SyncStandbysDefined.

Referenced by SyncRepInitConfig().

SyncRepGetSyncRecPtr()

static bool SyncRepGetSyncRecPtr ( XLogRecPtr *  writePtr, XLogRecPtr *  flushPtr, XLogRecPtr *  applyPtr, bool *  am_sync  )

static

Definition at line 543 of file syncrep.c.

{
    SyncRepStandbyData *sync_standbys;
    int         num_standbys;
    int         i;
 
    /* Initialize default results */
    *writePtr = InvalidXLogRecPtr;
    *flushPtr = InvalidXLogRecPtr;
    *applyPtr = InvalidXLogRecPtr;
    *am_sync = false;
 
    /* Quick out if not even configured to be synchronous */
    if (SyncRepConfig == NULL)
        return false;
 
    /* Get standbys that are considered as synchronous at this moment */
    num_standbys = SyncRepGetCandidateStandbys(&sync_standbys);
 
    /* Am I among the candidate sync standbys? */
    for (i = 0; i < num_standbys; i++)
    {
        if (sync_standbys[i].is_me)
        {
            *am_sync = true;
            break;
        }
    }
 
    /*
     * Nothing more to do if we are not managing a sync standby or there are
     * not enough synchronous standbys.
     */
    if (!(*am_sync) ||
        num_standbys < SyncRepConfig->num_sync)
    {
        pfree(sync_standbys);
        return false;
    }
 
    /*
     * In a priority-based sync replication, the synced positions are the
     * oldest ones among sync standbys. In a quorum-based, they are the Nth
     * latest ones.
     *
     * SyncRepGetNthLatestSyncRecPtr() also can calculate the oldest
     * positions. But we use SyncRepGetOldestSyncRecPtr() for that calculation
     * because it's a bit more efficient.
     *
     * XXX If the numbers of current and requested sync standbys are the same,
     * we can use SyncRepGetOldestSyncRecPtr() to calculate the synced
     * positions even in a quorum-based sync replication.
     */
    if (SyncRepConfig->syncrep_method == SYNC_REP_PRIORITY)
    {
        SyncRepGetOldestSyncRecPtr(writePtr, flushPtr, applyPtr,
                                   sync_standbys, num_standbys);
    }
    else
    {
        SyncRepGetNthLatestSyncRecPtr(writePtr, flushPtr, applyPtr,
                                      sync_standbys, num_standbys,
                                      SyncRepConfig->num_sync);
    }
 
    pfree(sync_standbys);
    return true;
}

References i, InvalidXLogRecPtr, SyncRepConfigData::num_sync, pfree(), SYNC_REP_PRIORITY, SyncRepConfigData::syncrep_method, SyncRepConfig, SyncRepGetCandidateStandbys(), SyncRepGetNthLatestSyncRecPtr(), and SyncRepGetOldestSyncRecPtr().

Referenced by SyncRepReleaseWaiters().

SyncRepInitConfig()

void SyncRepInitConfig

(

void

)

Definition at line 402 of file syncrep.c.

{
    int         priority;
 
    /*
     * Determine if we are a potential sync standby and remember the result
     * for handling replies from standby.
     */
    priority = SyncRepGetStandbyPriority();
    if (MyWalSnd->sync_standby_priority != priority)
    {
        SpinLockAcquire(&MyWalSnd->mutex);
        MyWalSnd->sync_standby_priority = priority;
        SpinLockRelease(&MyWalSnd->mutex);
 
        ereport(DEBUG1,
                (errmsg_internal("standby \"%s\" now has synchronous standby priority %d",
                                 application_name, priority)));
    }
}

References application_name, DEBUG1, ereport, errmsg_internal(), WalSnd::mutex, MyWalSnd, SpinLockAcquire, SpinLockRelease, WalSnd::sync_standby_priority, and SyncRepGetStandbyPriority().

Referenced by ProcessPendingWrites(), StartLogicalReplication(), StartReplication(), WalSndLoop(), and WalSndWaitForWal().

SyncRepQueueInsert()

static void SyncRepQueueInsert ( int  mode )

static

Definition at line 329 of file syncrep.c.

{
    dlist_head *queue;
    dlist_iter  iter;
 
    Assert(mode >= 0 && mode < NUM_SYNC_REP_WAIT_MODE);
    queue = &WalSndCtl->SyncRepQueue[mode];
 
    dlist_reverse_foreach(iter, queue)
    {
        PGPROC     *proc = dlist_container(PGPROC, syncRepLinks, iter.cur);
 
        /*
         * Stop at the queue element that we should insert after to ensure the
         * queue is ordered by LSN.
         */
        if (proc->waitLSN < MyProc->waitLSN)
        {
            dlist_insert_after(&proc->syncRepLinks, &MyProc->syncRepLinks);
            return;
        }
    }
 
    /*
     * If we get here, the list was either empty, or this process needs to be
     * at the head.
     */
    dlist_push_head(queue, &MyProc->syncRepLinks);
}

References Assert, dlist_iter::cur, dlist_container, dlist_insert_after(), dlist_push_head(), dlist_reverse_foreach, mode, MyProc, NUM_SYNC_REP_WAIT_MODE, PGPROC::syncRepLinks, WalSndCtlData::SyncRepQueue, PGPROC::waitLSN, and WalSndCtl.

Referenced by SyncRepWaitForLSN().

SyncRepReleaseWaiters()

void SyncRepReleaseWaiters

(

void

)

Definition at line 431 of file syncrep.c.

{
    volatile WalSndCtlData *walsndctl = WalSndCtl;
    XLogRecPtr  writePtr;
    XLogRecPtr  flushPtr;
    XLogRecPtr  applyPtr;
    bool        got_recptr;
    bool        am_sync;
    int         numwrite = 0;
    int         numflush = 0;
    int         numapply = 0;
 
    /*
     * If this WALSender is serving a standby that is not on the list of
     * potential sync standbys then we have nothing to do. If we are still
     * starting up, still running base backup or the current flush position is
     * still invalid, then leave quickly also.  Streaming or stopping WAL
     * senders are allowed to release waiters.
     */
    if (MyWalSnd->sync_standby_priority == 0 ||
        (MyWalSnd->state != WALSNDSTATE_STREAMING &&
         MyWalSnd->state != WALSNDSTATE_STOPPING) ||
        XLogRecPtrIsInvalid(MyWalSnd->flush))
    {
        announce_next_takeover = true;
        return;
    }
 
    /*
     * We're a potential sync standby. Release waiters if there are enough
     * sync standbys and we are considered as sync.
     */
    LWLockAcquire(SyncRepLock, LW_EXCLUSIVE);
 
    /*
     * Check whether we are a sync standby or not, and calculate the synced
     * positions among all sync standbys.  (Note: although this step does not
     * of itself require holding SyncRepLock, it seems like a good idea to do
     * it after acquiring the lock.  This ensures that the WAL pointers we use
     * to release waiters are newer than any previous execution of this
     * routine used.)
     */
    got_recptr = SyncRepGetSyncRecPtr(&writePtr, &flushPtr, &applyPtr, &am_sync);
 
    /*
     * If we are managing a sync standby, though we weren't prior to this,
     * then announce we are now a sync standby.
     */
    if (announce_next_takeover && am_sync)
    {
        announce_next_takeover = false;
 
        if (SyncRepConfig->syncrep_method == SYNC_REP_PRIORITY)
            ereport(LOG,
                    (errmsg("standby \"%s\" is now a synchronous standby with priority %d",
                            application_name, MyWalSnd->sync_standby_priority)));
        else
            ereport(LOG,
                    (errmsg("standby \"%s\" is now a candidate for quorum synchronous standby",
                            application_name)));
    }
 
    /*
     * If the number of sync standbys is less than requested or we aren't
     * managing a sync standby then just leave.
     */
    if (!got_recptr || !am_sync)
    {
        LWLockRelease(SyncRepLock);
        announce_next_takeover = !am_sync;
        return;
    }
 
    /*
     * Set the lsn first so that when we wake backends they will release up to
     * this location.
     */
    if (walsndctl->lsn[SYNC_REP_WAIT_WRITE] < writePtr)
    {
        walsndctl->lsn[SYNC_REP_WAIT_WRITE] = writePtr;
        numwrite = SyncRepWakeQueue(false, SYNC_REP_WAIT_WRITE);
    }
    if (walsndctl->lsn[SYNC_REP_WAIT_FLUSH] < flushPtr)
    {
        walsndctl->lsn[SYNC_REP_WAIT_FLUSH] = flushPtr;
        numflush = SyncRepWakeQueue(false, SYNC_REP_WAIT_FLUSH);
    }
    if (walsndctl->lsn[SYNC_REP_WAIT_APPLY] < applyPtr)
    {
        walsndctl->lsn[SYNC_REP_WAIT_APPLY] = applyPtr;
        numapply = SyncRepWakeQueue(false, SYNC_REP_WAIT_APPLY);
    }
 
    LWLockRelease(SyncRepLock);
 
    elog(DEBUG3, "released %d procs up to write %X/%X, %d procs up to flush %X/%X, %d procs up to apply %X/%X",
         numwrite, LSN_FORMAT_ARGS(writePtr),
         numflush, LSN_FORMAT_ARGS(flushPtr),
         numapply, LSN_FORMAT_ARGS(applyPtr));
}

References announce_next_takeover, application_name, DEBUG3, elog, ereport, errmsg(), WalSnd::flush, LOG, WalSndCtlData::lsn, LSN_FORMAT_ARGS, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), MyWalSnd, WalSnd::state, SYNC_REP_PRIORITY, SYNC_REP_WAIT_APPLY, SYNC_REP_WAIT_FLUSH, SYNC_REP_WAIT_WRITE, WalSnd::sync_standby_priority, SyncRepConfigData::syncrep_method, SyncRepConfig, SyncRepGetSyncRecPtr(), SyncRepWakeQueue(), WalSndCtl, WALSNDSTATE_STOPPING, WALSNDSTATE_STREAMING, and XLogRecPtrIsInvalid.

Referenced by ProcessStandbyReplyMessage().

SyncRepUpdateSyncStandbysDefined()

void SyncRepUpdateSyncStandbysDefined

(

void

)

Definition at line 921 of file syncrep.c.

{
    bool        sync_standbys_defined = SyncStandbysDefined();
 
    if (sync_standbys_defined != WalSndCtl->sync_standbys_defined)
    {
        LWLockAcquire(SyncRepLock, LW_EXCLUSIVE);
 
        /*
         * If synchronous_standby_names has been reset to empty, it's futile
         * for backends to continue waiting.  Since the user no longer wants
         * synchronous replication, we'd better wake them up.
         */
        if (!sync_standbys_defined)
        {
            int         i;
 
            for (i = 0; i < NUM_SYNC_REP_WAIT_MODE; i++)
                SyncRepWakeQueue(true, i);
        }
 
        /*
         * Only allow people to join the queue when there are synchronous
         * standbys defined.  Without this interlock, there's a race
         * condition: we might wake up all the current waiters; then, some
         * backend that hasn't yet reloaded its config might go to sleep on
         * the queue (and never wake up).  This prevents that.
         */
        WalSndCtl->sync_standbys_defined = sync_standbys_defined;
 
        LWLockRelease(SyncRepLock);
    }
}

References i, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), NUM_SYNC_REP_WAIT_MODE, WalSndCtlData::sync_standbys_defined, SyncRepWakeQueue(), SyncStandbysDefined, and WalSndCtl.

Referenced by UpdateSharedMemoryConfig().

SyncRepWaitForLSN()

void SyncRepWaitForLSN	(	XLogRecPtr	lsn,
		bool	commit
	)

Definition at line 148 of file syncrep.c.

{
    int         mode;
 
    /*
     * This should be called while holding interrupts during a transaction
     * commit to prevent the follow-up shared memory queue cleanups to be
     * influenced by external interruptions.
     */
    Assert(InterruptHoldoffCount > 0);
 
    /*
     * Fast exit if user has not requested sync replication, or there are no
     * sync replication standby names defined.
     *
     * Since this routine gets called every commit time, it's important to
     * exit quickly if sync replication is not requested. So we check
     * WalSndCtl->sync_standbys_defined flag without the lock and exit
     * immediately if it's false. If it's true, we need to check it again
     * later while holding the lock, to check the flag and operate the sync
     * rep queue atomically. This is necessary to avoid the race condition
     * described in SyncRepUpdateSyncStandbysDefined(). On the other hand, if
     * it's false, the lock is not necessary because we don't touch the queue.
     */
    if (!SyncRepRequested() ||
        !((volatile WalSndCtlData *) WalSndCtl)->sync_standbys_defined)
        return;
 
    /* Cap the level for anything other than commit to remote flush only. */
    if (commit)
        mode = SyncRepWaitMode;
    else
        mode = Min(SyncRepWaitMode, SYNC_REP_WAIT_FLUSH);
 
    Assert(dlist_node_is_detached(&MyProc->syncRepLinks));
    Assert(WalSndCtl != NULL);
 
    LWLockAcquire(SyncRepLock, LW_EXCLUSIVE);
    Assert(MyProc->syncRepState == SYNC_REP_NOT_WAITING);
 
    /*
     * We don't wait for sync rep if WalSndCtl->sync_standbys_defined is not
     * set.  See SyncRepUpdateSyncStandbysDefined.
     *
     * Also check that the standby hasn't already replied. Unlikely race
     * condition but we'll be fetching that cache line anyway so it's likely
     * to be a low cost check.
     */
    if (!WalSndCtl->sync_standbys_defined ||
        lsn <= WalSndCtl->lsn[mode])
    {
        LWLockRelease(SyncRepLock);
        return;
    }
 
    /*
     * Set our waitLSN so WALSender will know when to wake us, and add
     * ourselves to the queue.
     */
    MyProc->waitLSN = lsn;
    MyProc->syncRepState = SYNC_REP_WAITING;
    SyncRepQueueInsert(mode);
    Assert(SyncRepQueueIsOrderedByLSN(mode));
    LWLockRelease(SyncRepLock);
 
    /* Alter ps display to show waiting for sync rep. */
    if (update_process_title)
    {
        char        buffer[32];
 
        sprintf(buffer, "waiting for %X/%X", LSN_FORMAT_ARGS(lsn));
        set_ps_display_suffix(buffer);
    }
 
    /*
     * Wait for specified LSN to be confirmed.
     *
     * Each proc has its own wait latch, so we perform a normal latch
     * check/wait loop here.
     */
    for (;;)
    {
        int         rc;
 
        /* Must reset the latch before testing state. */
        ResetLatch(MyLatch);
 
        /*
         * Acquiring the lock is not needed, the latch ensures proper
         * barriers. If it looks like we're done, we must really be done,
         * because once walsender changes the state to SYNC_REP_WAIT_COMPLETE,
         * it will never update it again, so we can't be seeing a stale value
         * in that case.
         */
        if (MyProc->syncRepState == SYNC_REP_WAIT_COMPLETE)
            break;
 
        /*
         * If a wait for synchronous replication is pending, we can neither
         * acknowledge the commit nor raise ERROR or FATAL.  The latter would
         * lead the client to believe that the transaction aborted, which is
         * not true: it's already committed locally. The former is no good
         * either: the client has requested synchronous replication, and is
         * entitled to assume that an acknowledged commit is also replicated,
         * which might not be true. So in this case we issue a WARNING (which
         * some clients may be able to interpret) and shut off further output.
         * We do NOT reset ProcDiePending, so that the process will die after
         * the commit is cleaned up.
         */
        if (ProcDiePending)
        {
            ereport(WARNING,
                    (errcode(ERRCODE_ADMIN_SHUTDOWN),
                     errmsg("canceling the wait for synchronous replication and terminating connection due to administrator command"),
                     errdetail("The transaction has already committed locally, but might not have been replicated to the standby.")));
            whereToSendOutput = DestNone;
            SyncRepCancelWait();
            break;
        }
 
        /*
         * It's unclear what to do if a query cancel interrupt arrives.  We
         * can't actually abort at this point, but ignoring the interrupt
         * altogether is not helpful, so we just terminate the wait with a
         * suitable warning.
         */
        if (QueryCancelPending)
        {
            QueryCancelPending = false;
            ereport(WARNING,
                    (errmsg("canceling wait for synchronous replication due to user request"),
                     errdetail("The transaction has already committed locally, but might not have been replicated to the standby.")));
            SyncRepCancelWait();
            break;
        }
 
        /*
         * Wait on latch.  Any condition that should wake us up will set the
         * latch, so no need for timeout.
         */
        rc = WaitLatch(MyLatch, WL_LATCH_SET | WL_POSTMASTER_DEATH, -1,
                       WAIT_EVENT_SYNC_REP);
 
        /*
         * If the postmaster dies, we'll probably never get an acknowledgment,
         * because all the wal sender processes will exit. So just bail out.
         */
        if (rc & WL_POSTMASTER_DEATH)
        {
            ProcDiePending = true;
            whereToSendOutput = DestNone;
            SyncRepCancelWait();
            break;
        }
    }
 
    /*
     * WalSender has checked our LSN and has removed us from queue. Clean up
     * state and leave.  It's OK to reset these shared memory fields without
     * holding SyncRepLock, because any walsenders will ignore us anyway when
     * we're not on the queue.  We need a read barrier to make sure we see the
     * changes to the queue link (this might be unnecessary without
     * assertions, but better safe than sorry).
     */
    pg_read_barrier();
    Assert(dlist_node_is_detached(&MyProc->syncRepLinks));
    MyProc->syncRepState = SYNC_REP_NOT_WAITING;
    MyProc->waitLSN = 0;
 
    /* reset ps display to remove the suffix */
    if (update_process_title)
        set_ps_display_remove_suffix();
}

References Assert, DestNone, dlist_node_is_detached(), ereport, errcode(), errdetail(), errmsg(), InterruptHoldoffCount, LSN_FORMAT_ARGS, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), Min, mode, MyLatch, MyProc, pg_read_barrier, ProcDiePending, QueryCancelPending, ResetLatch(), set_ps_display_remove_suffix(), set_ps_display_suffix(), sprintf, SYNC_REP_NOT_WAITING, SYNC_REP_WAIT_COMPLETE, SYNC_REP_WAIT_FLUSH, SYNC_REP_WAITING, WalSndCtlData::sync_standbys_defined, SyncRepCancelWait(), PGPROC::syncRepLinks, SyncRepQueueInsert(), SyncRepRequested, PGPROC::syncRepState, SyncRepWaitMode, update_process_title, WaitLatch(), PGPROC::waitLSN, WalSndCtl, WARNING, whereToSendOutput, WL_LATCH_SET, and WL_POSTMASTER_DEATH.

Referenced by EndPrepare(), RecordTransactionAbortPrepared(), RecordTransactionCommit(), and RecordTransactionCommitPrepared().

SyncRepWakeQueue()

static int SyncRepWakeQueue ( bool  all, int  mode  )

static

Definition at line 864 of file syncrep.c.

{
    volatile WalSndCtlData *walsndctl = WalSndCtl;
    int         numprocs = 0;
    dlist_mutable_iter iter;
 
    Assert(mode >= 0 && mode < NUM_SYNC_REP_WAIT_MODE);
    Assert(LWLockHeldByMeInMode(SyncRepLock, LW_EXCLUSIVE));
    Assert(SyncRepQueueIsOrderedByLSN(mode));
 
    dlist_foreach_modify(iter, &WalSndCtl->SyncRepQueue[mode])
    {
        PGPROC     *proc = dlist_container(PGPROC, syncRepLinks, iter.cur);
 
        /*
         * Assume the queue is ordered by LSN
         */
        if (!all && walsndctl->lsn[mode] < proc->waitLSN)
            return numprocs;
 
        /*
         * Remove from queue.
         */
        dlist_delete_thoroughly(&proc->syncRepLinks);
 
        /*
         * SyncRepWaitForLSN() reads syncRepState without holding the lock, so
         * make sure that it sees the queue link being removed before the
         * syncRepState change.
         */
        pg_write_barrier();
 
        /*
         * Set state to complete; see SyncRepWaitForLSN() for discussion of
         * the various states.
         */
        proc->syncRepState = SYNC_REP_WAIT_COMPLETE;
 
        /*
         * Wake only when we have set state and removed from queue.
         */
        SetLatch(&(proc->procLatch));
 
        numprocs++;
    }
 
    return numprocs;
}

References Assert, dlist_mutable_iter::cur, dlist_container, dlist_delete_thoroughly(), dlist_foreach_modify, WalSndCtlData::lsn, LW_EXCLUSIVE, LWLockHeldByMeInMode(), mode, NUM_SYNC_REP_WAIT_MODE, pg_write_barrier, PGPROC::procLatch, SetLatch(), SYNC_REP_WAIT_COMPLETE, PGPROC::syncRepLinks, WalSndCtlData::SyncRepQueue, PGPROC::syncRepState, PGPROC::waitLSN, and WalSndCtl.

Referenced by SyncRepReleaseWaiters(), and SyncRepUpdateSyncStandbysDefined().

Variable Documentation

announce_next_takeover

bool announce_next_takeover = true

static

Definition at line 95 of file syncrep.c.

Referenced by SyncRepReleaseWaiters().

SyncRepConfig

SyncRepConfigData* SyncRepConfig = NULL

Definition at line 97 of file syncrep.c.

Referenced by assign_synchronous_standby_names(), pg_stat_get_wal_senders(), SyncRepGetCandidateStandbys(), SyncRepGetStandbyPriority(), SyncRepGetSyncRecPtr(), and SyncRepReleaseWaiters().

SyncRepStandbyNames

char* SyncRepStandbyNames

Definition at line 90 of file syncrep.c.

SyncRepWaitMode

int SyncRepWaitMode = SYNC_REP_NO_WAIT

static

Definition at line 98 of file syncrep.c.

Referenced by assign_synchronous_commit(), and SyncRepWaitForLSN().