syncrep.h File Reference

#include "access/xlogdefs.h"

Include dependency graph for syncrep.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Data Structures
struct	SyncRepStandbyData
struct	SyncRepConfigData

Macros
#define	SyncRepRequested()    (max_wal_senders > 0 && synchronous_commit > SYNCHRONOUS_COMMIT_LOCAL_FLUSH)
#define	SYNC_REP_NO_WAIT   (-1)
#define	SYNC_REP_WAIT_WRITE   0
#define	SYNC_REP_WAIT_FLUSH   1
#define	SYNC_REP_WAIT_APPLY   2
#define	NUM_SYNC_REP_WAIT_MODE   3
#define	SYNC_REP_NOT_WAITING   0
#define	SYNC_REP_WAITING   1
#define	SYNC_REP_WAIT_COMPLETE   2
#define	SYNC_REP_PRIORITY   0
#define	SYNC_REP_QUORUM   1

Typedefs
typedef struct SyncRepStandbyData	SyncRepStandbyData
typedef struct SyncRepConfigData	SyncRepConfigData

Functions
void	SyncRepWaitForLSN (XLogRecPtr lsn, bool commit)
void	SyncRepCleanupAtProcExit (void)
void	SyncRepInitConfig (void)
void	SyncRepReleaseWaiters (void)
int	SyncRepGetCandidateStandbys (SyncRepStandbyData **standbys)
void	SyncRepUpdateSyncStandbysDefined (void)
int	syncrep_yyparse (void)
int	syncrep_yylex (void)
void	syncrep_yyerror (const char *str)
void	syncrep_scanner_init (const char *str)
void	syncrep_scanner_finish (void)

Variables
PGDLLIMPORT SyncRepConfigData *	SyncRepConfig
PGDLLIMPORT SyncRepConfigData *	syncrep_parse_result
PGDLLIMPORT char *	syncrep_parse_error_msg
PGDLLIMPORT char *	SyncRepStandbyNames

Macro Definition Documentation

NUM_SYNC_REP_WAIT_MODE

#define NUM_SYNC_REP_WAIT_MODE   3

Definition at line 27 of file syncrep.h.

SYNC_REP_NO_WAIT

#define SYNC_REP_NO_WAIT   (-1)

Definition at line 22 of file syncrep.h.

SYNC_REP_NOT_WAITING

#define SYNC_REP_NOT_WAITING   0

Definition at line 30 of file syncrep.h.

SYNC_REP_PRIORITY

#define SYNC_REP_PRIORITY   0

Definition at line 35 of file syncrep.h.

SYNC_REP_QUORUM

#define SYNC_REP_QUORUM   1

Definition at line 36 of file syncrep.h.

SYNC_REP_WAIT_APPLY

#define SYNC_REP_WAIT_APPLY   2

Definition at line 25 of file syncrep.h.

SYNC_REP_WAIT_COMPLETE

#define SYNC_REP_WAIT_COMPLETE   2

Definition at line 32 of file syncrep.h.

SYNC_REP_WAIT_FLUSH

#define SYNC_REP_WAIT_FLUSH   1

Definition at line 24 of file syncrep.h.

SYNC_REP_WAIT_WRITE

#define SYNC_REP_WAIT_WRITE   0

Definition at line 23 of file syncrep.h.

SYNC_REP_WAITING

#define SYNC_REP_WAITING   1

Definition at line 31 of file syncrep.h.

SyncRepRequested

#define SyncRepRequested

(

)

(max_wal_senders > 0 && synchronous_commit > SYNCHRONOUS_COMMIT_LOCAL_FLUSH)

Definition at line 18 of file syncrep.h.

Typedef Documentation

SyncRepConfigData

typedef struct SyncRepConfigData SyncRepConfigData

SyncRepStandbyData

typedef struct SyncRepStandbyData SyncRepStandbyData

Function Documentation

syncrep_scanner_finish()

void syncrep_scanner_finish

(

void

)

Referenced by check_synchronous_standby_names().

syncrep_scanner_init()

void syncrep_scanner_init

(

const char *

str

)

Referenced by check_synchronous_standby_names().

syncrep_yyerror()

void syncrep_yyerror

(

const char *

str

)

syncrep_yylex()

int syncrep_yylex

(

void

)

syncrep_yyparse()

int syncrep_yyparse

(

void

)

Referenced by check_synchronous_standby_names().

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().

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().

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().

Variable Documentation

syncrep_parse_error_msg

PGDLLIMPORT char* syncrep_parse_error_msg

extern

Referenced by check_synchronous_standby_names().

syncrep_parse_result

PGDLLIMPORT SyncRepConfigData* syncrep_parse_result

extern

Referenced by check_synchronous_standby_names().

SyncRepConfig

PGDLLIMPORT SyncRepConfigData* SyncRepConfig

extern

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

PGDLLIMPORT char* SyncRepStandbyNames

extern

Definition at line 90 of file syncrep.c.