From 39857e15fac0a7b5b3105b730db4dfb271788cca Mon Sep 17 00:00:00 2001 From: alterego655 <824662526@qq.com> Date: Wed, 15 Oct 2025 15:47:27 +0800 Subject: [PATCH v16 2/3] Add infrastructure for efficient LSN waiting Implement a new facility that allows processes to wait for WAL to reach specific LSNs, both on primary (waiting for flush) and standby (waiting for replay) servers. The implementation uses shared memory with per-backend information organized into pairing heaps, allowing O(1) access to the minimum waited LSN. This enables fast-path checks: after replaying or flushing WAL, the startup process or WAL writer can quickly determine if any waiters need to be awakened. Key components: - New xlogwait.c/h module with WaitForLSNReplay() and WaitForLSNFlush() - Separate pairing heaps for replay and flush waiters - WaitLSN lightweight lock for coordinating shared state - Wait events WAIT_FOR_WAL_REPLAY and WAIT_FOR_WAL_FLUSH for monitoring This infrastructure can be used by features that need to wait for WAL operations to complete. Discussion: https://www.postgresql.org/message-id/flat/CAPpHfdsjtZLVzxjGT8rJHCYbM0D5dwkO+BBjcirozJ6nYbOW8Q@mail.gmail.com https://www.postgresql.org/message-id/flat/CABPTF7UNft368x-RgOXkfj475OwEbp%2BVVO-wEXz7StgjD_%3D6sw%40mail.gmail.com Author: Kartyshov Ivan Author: Alexander Korotkov Author: Xuneng Zhou Reviewed-by: Michael Paquier Reviewed-by: Peter Eisentraut Reviewed-by: Dilip Kumar Reviewed-by: Amit Kapila Reviewed-by: Alexander Lakhin Reviewed-by: Bharath Rupireddy Reviewed-by: Euler Taveira Reviewed-by: Heikki Linnakangas Reviewed-by: Kyotaro Horiguchi --- src/backend/access/transam/Makefile | 3 +- src/backend/access/transam/meson.build | 1 + src/backend/access/transam/xlogwait.c | 503 ++++++++++++++++++ src/backend/storage/ipc/ipci.c | 3 + .../utils/activity/wait_event_names.txt | 3 + src/include/access/xlogwait.h | 112 ++++ src/include/storage/lwlocklist.h | 1 + 7 files changed, 625 insertions(+), 1 deletion(-) create mode 100644 src/backend/access/transam/xlogwait.c create mode 100644 src/include/access/xlogwait.h diff --git a/src/backend/access/transam/Makefile b/src/backend/access/transam/Makefile index 661c55a9db7..a32f473e0a2 100644 --- a/src/backend/access/transam/Makefile +++ b/src/backend/access/transam/Makefile @@ -36,7 +36,8 @@ OBJS = \ xlogreader.o \ xlogrecovery.o \ xlogstats.o \ - xlogutils.o + xlogutils.o \ + xlogwait.o include $(top_srcdir)/src/backend/common.mk diff --git a/src/backend/access/transam/meson.build b/src/backend/access/transam/meson.build index e8ae9b13c8e..74a62ab3eab 100644 --- a/src/backend/access/transam/meson.build +++ b/src/backend/access/transam/meson.build @@ -24,6 +24,7 @@ backend_sources += files( 'xlogrecovery.c', 'xlogstats.c', 'xlogutils.c', + 'xlogwait.c', ) # used by frontend programs to build a frontend xlogreader diff --git a/src/backend/access/transam/xlogwait.c b/src/backend/access/transam/xlogwait.c new file mode 100644 index 00000000000..49dae7ac1c4 --- /dev/null +++ b/src/backend/access/transam/xlogwait.c @@ -0,0 +1,503 @@ +/*------------------------------------------------------------------------- + * + * xlogwait.c + * Implements waiting for WAL operations to reach specific LSNs. + * + * Copyright (c) 2025, PostgreSQL Global Development Group + * + * IDENTIFICATION + * src/backend/access/transam/xlogwait.c + * + * NOTES + * This file implements waiting for WAL operations to reach specific LSNs + * on both physical standby and primary servers. The core idea is simple: + * every process that wants to wait publishes the LSN it needs to the + * shared memory, and the appropriate process (startup on standby, or + * WAL writer/backend on primary) wakes it once that LSN has been reached. + * + * The shared memory used by this module comprises a procInfos + * per-backend array with the information of the awaited LSN for each + * of the backend processes. The elements of that array are organized + * into a pairing heap waitersHeap, which allows for very fast finding + * of the least awaited LSN. + * + * In addition, the least-awaited LSN is cached as minWaitedLSN. The + * waiter process publishes information about itself to the shared + * memory and waits on the latch before it wakens up by the appropriate + * process, standby is promoted, or the postmaster dies. Then, it cleans + * information about itself in the shared memory. + * + * On standby servers: After replaying a WAL record, the startup process + * first performs a fast path check minWaitedLSN > replayLSN. If this + * check is negative, it checks waitersHeap and wakes up the backend + * whose awaited LSNs are reached. + * + * On primary servers: After flushing WAL, the WAL writer or backend + * process performs a similar check against the flush LSN and wakes up + * waiters whose target flush LSNs have been reached. + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include +#include + +#include "access/xlog.h" +#include "access/xlogrecovery.h" +#include "access/xlogwait.h" +#include "miscadmin.h" +#include "pgstat.h" +#include "storage/latch.h" +#include "storage/proc.h" +#include "storage/shmem.h" +#include "utils/fmgrprotos.h" +#include "utils/pg_lsn.h" +#include "utils/snapmgr.h" + + +static int waitlsn_replay_cmp(const pairingheap_node *a, const pairingheap_node *b, + void *arg); + +static int waitlsn_flush_cmp(const pairingheap_node *a, const pairingheap_node *b, + void *arg); + +struct WaitLSNState *waitLSNState = NULL; + +/* Report the amount of shared memory space needed for WaitLSNState. */ +Size +WaitLSNShmemSize(void) +{ + Size size; + + size = offsetof(WaitLSNState, procInfos); + size = add_size(size, mul_size(MaxBackends + NUM_AUXILIARY_PROCS, sizeof(WaitLSNProcInfo))); + return size; +} + +/* Initialize the WaitLSNState in the shared memory. */ +void +WaitLSNShmemInit(void) +{ + bool found; + + waitLSNState = (WaitLSNState *) ShmemInitStruct("WaitLSNState", + WaitLSNShmemSize(), + &found); + if (!found) + { + /* Initialize replay heap and tracking */ + pg_atomic_init_u64(&waitLSNState->minWaitedReplayLSN, PG_UINT64_MAX); + pairingheap_initialize(&waitLSNState->replayWaitersHeap, waitlsn_replay_cmp, (void *)(uintptr_t)WAIT_LSN_REPLAY); + + /* Initialize flush heap and tracking */ + pg_atomic_init_u64(&waitLSNState->minWaitedFlushLSN, PG_UINT64_MAX); + pairingheap_initialize(&waitLSNState->flushWaitersHeap, waitlsn_flush_cmp, (void *)(uintptr_t)WAIT_LSN_FLUSH); + + /* Initialize process info array */ + memset(&waitLSNState->procInfos, 0, + (MaxBackends + NUM_AUXILIARY_PROCS) * sizeof(WaitLSNProcInfo)); + } +} + +/* + * Comparison function for replay waiters heaps. Waiting processes are + * ordered by LSN, so that the waiter with smallest LSN is at the top. + */ +static int +waitlsn_replay_cmp(const pairingheap_node *a, const pairingheap_node *b, void *arg) +{ + const WaitLSNProcInfo *aproc = pairingheap_const_container(WaitLSNProcInfo, replayHeapNode, a); + const WaitLSNProcInfo *bproc = pairingheap_const_container(WaitLSNProcInfo, replayHeapNode, b); + + if (aproc->waitLSN < bproc->waitLSN) + return 1; + else if (aproc->waitLSN > bproc->waitLSN) + return -1; + else + return 0; +} + +/* + * Comparison function for flush waiters heaps. Waiting processes are + * ordered by LSN, so that the waiter with smallest LSN is at the top. + */ +static int +waitlsn_flush_cmp(const pairingheap_node *a, const pairingheap_node *b, void *arg) +{ + const WaitLSNProcInfo *aproc = pairingheap_const_container(WaitLSNProcInfo, flushHeapNode, a); + const WaitLSNProcInfo *bproc = pairingheap_const_container(WaitLSNProcInfo, flushHeapNode, b); + + if (aproc->waitLSN < bproc->waitLSN) + return 1; + else if (aproc->waitLSN > bproc->waitLSN) + return -1; + else + return 0; +} + +/* + * Update minimum waited LSN for the specified operation type + */ +static void +updateMinWaitedLSN(WaitLSNOperation operation) +{ + XLogRecPtr minWaitedLSN = PG_UINT64_MAX; + + if (operation == WAIT_LSN_REPLAY) + { + if (!pairingheap_is_empty(&waitLSNState->replayWaitersHeap)) + { + pairingheap_node *node = pairingheap_first(&waitLSNState->replayWaitersHeap); + WaitLSNProcInfo *procInfo = pairingheap_container(WaitLSNProcInfo, replayHeapNode, node); + minWaitedLSN = procInfo->waitLSN; + } + pg_atomic_write_u64(&waitLSNState->minWaitedReplayLSN, minWaitedLSN); + } + else /* WAIT_LSN_FLUSH */ + { + if (!pairingheap_is_empty(&waitLSNState->flushWaitersHeap)) + { + pairingheap_node *node = pairingheap_first(&waitLSNState->flushWaitersHeap); + WaitLSNProcInfo *procInfo = pairingheap_container(WaitLSNProcInfo, flushHeapNode, node); + minWaitedLSN = procInfo->waitLSN; + } + pg_atomic_write_u64(&waitLSNState->minWaitedFlushLSN, minWaitedLSN); + } +} + +/* + * Add current process to appropriate waiters heap based on operation type + */ +static void +addLSNWaiter(XLogRecPtr lsn, WaitLSNOperation operation) +{ + WaitLSNProcInfo *procInfo = &waitLSNState->procInfos[MyProcNumber]; + + LWLockAcquire(WaitLSNLock, LW_EXCLUSIVE); + + procInfo->procno = MyProcNumber; + procInfo->waitLSN = lsn; + + if (operation == WAIT_LSN_REPLAY) + { + Assert(!procInfo->inReplayHeap); + pairingheap_add(&waitLSNState->replayWaitersHeap, &procInfo->replayHeapNode); + procInfo->inReplayHeap = true; + updateMinWaitedLSN(WAIT_LSN_REPLAY); + } + else /* WAIT_LSN_FLUSH */ + { + Assert(!procInfo->inFlushHeap); + pairingheap_add(&waitLSNState->flushWaitersHeap, &procInfo->flushHeapNode); + procInfo->inFlushHeap = true; + updateMinWaitedLSN(WAIT_LSN_FLUSH); + } + + LWLockRelease(WaitLSNLock); +} + +/* + * Remove current process from appropriate waiters heap based on operation type + */ +static void +deleteLSNWaiter(WaitLSNOperation operation) +{ + WaitLSNProcInfo *procInfo = &waitLSNState->procInfos[MyProcNumber]; + + LWLockAcquire(WaitLSNLock, LW_EXCLUSIVE); + + if (operation == WAIT_LSN_REPLAY && procInfo->inReplayHeap) + { + pairingheap_remove(&waitLSNState->replayWaitersHeap, &procInfo->replayHeapNode); + procInfo->inReplayHeap = false; + updateMinWaitedLSN(WAIT_LSN_REPLAY); + } + else if (operation == WAIT_LSN_FLUSH && procInfo->inFlushHeap) + { + pairingheap_remove(&waitLSNState->flushWaitersHeap, &procInfo->flushHeapNode); + procInfo->inFlushHeap = false; + updateMinWaitedLSN(WAIT_LSN_FLUSH); + } + + LWLockRelease(WaitLSNLock); +} + +/* + * Size of a static array of procs to wakeup by WaitLSNWakeup() allocated + * on the stack. It should be enough to take single iteration for most cases. + */ +#define WAKEUP_PROC_STATIC_ARRAY_SIZE (16) + +/* + * Remove waiters whose LSN has been reached from the heap and set their + * latches. If InvalidXLogRecPtr is given, remove all waiters from the heap + * and set latches for all waiters. + * + * This function first accumulates waiters to wake up into an array, then + * wakes them up without holding a WaitLSNLock. The array size is static and + * equal to WAKEUP_PROC_STATIC_ARRAY_SIZE. That should be more than enough + * to wake up all the waiters at once in the vast majority of cases. However, + * if there are more waiters, this function will loop to process them in + * multiple chunks. + */ +static void +wakeupWaiters(WaitLSNOperation operation, XLogRecPtr currentLSN) +{ + ProcNumber wakeUpProcs[WAKEUP_PROC_STATIC_ARRAY_SIZE]; + int numWakeUpProcs; + int i; + pairingheap *heap; + + /* Select appropriate heap */ + heap = (operation == WAIT_LSN_REPLAY) ? + &waitLSNState->replayWaitersHeap : + &waitLSNState->flushWaitersHeap; + + do + { + numWakeUpProcs = 0; + LWLockAcquire(WaitLSNLock, LW_EXCLUSIVE); + + /* + * Iterate the waiters heap until we find LSN not yet reached. + * Record process numbers to wake up, but send wakeups after releasing lock. + */ + while (!pairingheap_is_empty(heap)) + { + pairingheap_node *node = pairingheap_first(heap); + WaitLSNProcInfo *procInfo; + + /* Get procInfo using appropriate heap node */ + if (operation == WAIT_LSN_REPLAY) + procInfo = pairingheap_container(WaitLSNProcInfo, replayHeapNode, node); + else + procInfo = pairingheap_container(WaitLSNProcInfo, flushHeapNode, node); + + if (!XLogRecPtrIsInvalid(currentLSN) && procInfo->waitLSN > currentLSN) + break; + + Assert(numWakeUpProcs < WAKEUP_PROC_STATIC_ARRAY_SIZE); + wakeUpProcs[numWakeUpProcs++] = procInfo->procno; + (void) pairingheap_remove_first(heap); + + /* Update appropriate flag */ + if (operation == WAIT_LSN_REPLAY) + procInfo->inReplayHeap = false; + else + procInfo->inFlushHeap = false; + + if (numWakeUpProcs == WAKEUP_PROC_STATIC_ARRAY_SIZE) + break; + } + + updateMinWaitedLSN(operation); + LWLockRelease(WaitLSNLock); + + /* + * Set latches for processes, whose waited LSNs are already reached. + * As the time consuming operations, we do this outside of + * WaitLSNLock. This is actually fine because procLatch isn't ever + * freed, so we just can potentially set the wrong process' (or no + * process') latch. + */ + for (i = 0; i < numWakeUpProcs; i++) + SetLatch(&GetPGProcByNumber(wakeUpProcs[i])->procLatch); + + } while (numWakeUpProcs == WAKEUP_PROC_STATIC_ARRAY_SIZE); +} + +/* + * Wake up processes waiting for replay LSN to reach currentLSN + */ +void +WaitLSNWakeupReplay(XLogRecPtr currentLSN) +{ + /* Fast path check */ + if (pg_atomic_read_u64(&waitLSNState->minWaitedReplayLSN) > currentLSN) + return; + + wakeupWaiters(WAIT_LSN_REPLAY, currentLSN); +} + +/* + * Wake up processes waiting for flush LSN to reach currentLSN + */ +void +WaitLSNWakeupFlush(XLogRecPtr currentLSN) +{ + /* Fast path check */ + if (pg_atomic_read_u64(&waitLSNState->minWaitedFlushLSN) > currentLSN) + return; + + wakeupWaiters(WAIT_LSN_FLUSH, currentLSN); +} + +/* + * Clean up LSN waiters for exiting process + */ +void +WaitLSNCleanup(void) +{ + if (waitLSNState) + { + /* + * We do a fast-path check of the heap flags without the lock. These + * flags are set to true only by the process itself. So, it's only possible + * to get a false positive. But that will be eliminated by a recheck + * inside deleteLSNWaiter(). + */ + if (waitLSNState->procInfos[MyProcNumber].inReplayHeap) + deleteLSNWaiter(WAIT_LSN_REPLAY); + if (waitLSNState->procInfos[MyProcNumber].inFlushHeap) + deleteLSNWaiter(WAIT_LSN_FLUSH); + } +} + +/* + * Wait using MyLatch till the given LSN is replayed, the replica gets + * promoted, or the postmaster dies. + * + * Returns WAIT_LSN_RESULT_SUCCESS if target LSN was replayed. + * Returns WAIT_LSN_RESULT_NOT_IN_RECOVERY if run not in recovery, + * or replica got promoted before the target LSN replayed. + */ +WaitLSNResult +WaitForLSNReplay(XLogRecPtr targetLSN) +{ + XLogRecPtr currentLSN; + int wake_events = WL_LATCH_SET | WL_POSTMASTER_DEATH; + + /* Shouldn't be called when shmem isn't initialized */ + Assert(waitLSNState); + + /* Should have a valid proc number */ + Assert(MyProcNumber >= 0 && MyProcNumber < MaxBackends); + + /* + * Add our process to the replay waiters heap. It might happen that + * target LSN gets replayed before we do. Another check at the beginning + * of the loop below prevents the race condition. + */ + addLSNWaiter(targetLSN, WAIT_LSN_REPLAY); + + for (;;) + { + int rc; + currentLSN = GetXLogReplayRecPtr(NULL); + + /* Recheck that recovery is still in-progress */ + if (!RecoveryInProgress()) + { + /* + * Recovery was ended, but recheck if target LSN was already + * replayed. See the comment regarding deleteLSNWaiter() below. + */ + deleteLSNWaiter(WAIT_LSN_REPLAY); + + if (PromoteIsTriggered() && targetLSN <= currentLSN) + return WAIT_LSN_RESULT_SUCCESS; + return WAIT_LSN_RESULT_NOT_IN_RECOVERY; + } + else + { + /* Check if the waited LSN has been replayed */ + if (targetLSN <= currentLSN) + break; + } + + CHECK_FOR_INTERRUPTS(); + + rc = WaitLatch(MyLatch, wake_events, -1, + WAIT_EVENT_WAIT_FOR_WAL_REPLAY); + + /* + * Emergency bailout if postmaster has died. This is to avoid the + * necessity for manual cleanup of all postmaster children. + */ + if (rc & WL_POSTMASTER_DEATH) + ereport(FATAL, + (errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("terminating connection due to unexpected postmaster exit"), + errcontext("while waiting for LSN replay"))); + + if (rc & WL_LATCH_SET) + ResetLatch(MyLatch); + } + + /* + * Delete our process from the shared memory replay heap. We might + * already be deleted by the startup process. The 'inReplayHeap' flag prevents + * us from the double deletion. + */ + deleteLSNWaiter(WAIT_LSN_REPLAY); + + return WAIT_LSN_RESULT_SUCCESS; +} + +/* + * Wait until targetLSN has been flushed on a primary server. + * Returns only after the condition is satisfied or on FATAL exit. + */ +void +WaitForLSNFlush(XLogRecPtr targetLSN) +{ + XLogRecPtr currentLSN; + int wake_events = WL_LATCH_SET | WL_POSTMASTER_DEATH; + + /* Shouldn't be called when shmem isn't initialized */ + Assert(waitLSNState); + + /* Should have a valid proc number */ + Assert(MyProcNumber >= 0 && MyProcNumber < MaxBackends + NUM_AUXILIARY_PROCS); + + /* We can only wait for flush when we are not in recovery */ + Assert(!RecoveryInProgress()); + + /* Quick exit if already flushed */ + currentLSN = GetFlushRecPtr(NULL); + if (targetLSN <= currentLSN) + return; + + /* Add to flush waiters */ + addLSNWaiter(targetLSN, WAIT_LSN_FLUSH); + + /* Wait loop */ + for (;;) + { + int rc; + + /* Check if the waited LSN has been flushed */ + currentLSN = GetFlushRecPtr(NULL); + if (targetLSN <= currentLSN) + break; + + CHECK_FOR_INTERRUPTS(); + + rc = WaitLatch(MyLatch, wake_events, -1, + WAIT_EVENT_WAIT_FOR_WAL_FLUSH); + + /* + * Emergency bailout if postmaster has died. This is to avoid the + * necessity for manual cleanup of all postmaster children. + */ + if (rc & WL_POSTMASTER_DEATH) + ereport(FATAL, + (errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("terminating connection due to unexpected postmaster exit"), + errcontext("while waiting for LSN flush"))); + + if (rc & WL_LATCH_SET) + ResetLatch(MyLatch); + } + + /* + * Delete our process from the shared memory flush heap. We might + * already be deleted by the waker process. The 'inFlushHeap' flag prevents + * us from the double deletion. + */ + deleteLSNWaiter(WAIT_LSN_FLUSH); + + return; +} diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 2fa045e6b0f..10ffce8d174 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -24,6 +24,7 @@ #include "access/twophase.h" #include "access/xlogprefetcher.h" #include "access/xlogrecovery.h" +#include "access/xlogwait.h" #include "commands/async.h" #include "miscadmin.h" #include "pgstat.h" @@ -150,6 +151,7 @@ CalculateShmemSize(int *num_semaphores) size = add_size(size, InjectionPointShmemSize()); size = add_size(size, SlotSyncShmemSize()); size = add_size(size, AioShmemSize()); + size = add_size(size, WaitLSNShmemSize()); /* include additional requested shmem from preload libraries */ size = add_size(size, total_addin_request); @@ -343,6 +345,7 @@ CreateOrAttachShmemStructs(void) WaitEventCustomShmemInit(); InjectionPointShmemInit(); AioShmemInit(); + WaitLSNShmemInit(); } /* diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt index 7553f6eacef..c1ac71ff7f2 100644 --- a/src/backend/utils/activity/wait_event_names.txt +++ b/src/backend/utils/activity/wait_event_names.txt @@ -89,6 +89,8 @@ LIBPQWALRECEIVER_CONNECT "Waiting in WAL receiver to establish connection to rem LIBPQWALRECEIVER_RECEIVE "Waiting in WAL receiver to receive data from remote server." SSL_OPEN_SERVER "Waiting for SSL while attempting connection." WAIT_FOR_STANDBY_CONFIRMATION "Waiting for WAL to be received and flushed by the physical standby." +WAIT_FOR_WAL_FLUSH "Waiting for WAL flush to reach a target LSN on a primary." +WAIT_FOR_WAL_REPLAY "Waiting for WAL replay to reach a target LSN on a standby." WAL_SENDER_WAIT_FOR_WAL "Waiting for WAL to be flushed in WAL sender process." WAL_SENDER_WRITE_DATA "Waiting for any activity when processing replies from WAL receiver in WAL sender process." @@ -355,6 +357,7 @@ DSMRegistry "Waiting to read or update the dynamic shared memory registry." InjectionPoint "Waiting to read or update information related to injection points." SerialControl "Waiting to read or update shared pg_serial state." AioWorkerSubmissionQueue "Waiting to access AIO worker submission queue." +WaitLSN "Waiting to read or update shared Wait-for-LSN state." # # END OF PREDEFINED LWLOCKS (DO NOT CHANGE THIS LINE) diff --git a/src/include/access/xlogwait.h b/src/include/access/xlogwait.h new file mode 100644 index 00000000000..ada2a460ca4 --- /dev/null +++ b/src/include/access/xlogwait.h @@ -0,0 +1,112 @@ +/*------------------------------------------------------------------------- + * + * xlogwait.h + * Declarations for LSN replay waiting routines. + * + * Copyright (c) 2025, PostgreSQL Global Development Group + * + * src/include/access/xlogwait.h + * + *------------------------------------------------------------------------- + */ +#ifndef XLOG_WAIT_H +#define XLOG_WAIT_H + +#include "access/xlogdefs.h" +#include "lib/pairingheap.h" +#include "port/atomics.h" +#include "storage/procnumber.h" +#include "storage/spin.h" +#include "tcop/dest.h" + +/* + * Result statuses for WaitForLSNReplay(). + */ +typedef enum +{ + WAIT_LSN_RESULT_SUCCESS, /* Target LSN is reached */ + WAIT_LSN_RESULT_NOT_IN_RECOVERY, /* Recovery ended before or during our + * wait */ +} WaitLSNResult; + +/* + * Wait operation types for LSN waiting facility. + */ +typedef enum WaitLSNOperation +{ + WAIT_LSN_REPLAY, /* Waiting for replay on standby */ + WAIT_LSN_FLUSH /* Waiting for flush on primary */ +} WaitLSNOperation; + +/* + * WaitLSNProcInfo - the shared memory structure representing information + * about the single process, which may wait for LSN operations. An item of + * waitLSNState->procInfos array. + */ +typedef struct WaitLSNProcInfo +{ + /* LSN, which this process is waiting for */ + XLogRecPtr waitLSN; + + /* Process to wake up once the waitLSN is reached */ + ProcNumber procno; + + /* Type-safe heap membership flags */ + bool inReplayHeap; /* In replay waiters heap */ + bool inFlushHeap; /* In flush waiters heap */ + + /* Separate heap nodes for type safety */ + pairingheap_node replayHeapNode; + pairingheap_node flushHeapNode; +} WaitLSNProcInfo; + +/* + * WaitLSNState - the shared memory state for the LSN waiting facility. + */ +typedef struct WaitLSNState +{ + /* + * The minimum replay LSN value some process is waiting for. Used for the + * fast-path checking if we need to wake up any waiters after replaying a + * WAL record. Could be read lock-less. Update protected by WaitLSNLock. + */ + pg_atomic_uint64 minWaitedReplayLSN; + + /* + * A pairing heap of replay waiting processes ordered by LSN values (least LSN is + * on top). Protected by WaitLSNLock. + */ + pairingheap replayWaitersHeap; + + /* + * The minimum flush LSN value some process is waiting for. Used for the + * fast-path checking if we need to wake up any waiters after flushing + * WAL. Could be read lock-less. Update protected by WaitLSNLock. + */ + pg_atomic_uint64 minWaitedFlushLSN; + + /* + * A pairing heap of flush waiting processes ordered by LSN values (least LSN is + * on top). Protected by WaitLSNLock. + */ + pairingheap flushWaitersHeap; + + /* + * An array with per-process information, indexed by the process number. + * Protected by WaitLSNLock. + */ + WaitLSNProcInfo procInfos[FLEXIBLE_ARRAY_MEMBER]; +} WaitLSNState; + + +extern PGDLLIMPORT WaitLSNState *waitLSNState; + +extern Size WaitLSNShmemSize(void); +extern void WaitLSNShmemInit(void); +extern void WaitLSNWakeupReplay(XLogRecPtr currentLSN); +extern void WaitLSNWakeupFlush(XLogRecPtr currentLSN); +extern void WaitLSNCleanup(void); +extern WaitLSNResult WaitForLSNReplay(XLogRecPtr targetLSN); +extern void WaitForLSNFlush(XLogRecPtr targetLSN); + +#endif /* XLOG_WAIT_H */ diff --git a/src/include/storage/lwlocklist.h b/src/include/storage/lwlocklist.h index 06a1ffd4b08..5b0ce383408 100644 --- a/src/include/storage/lwlocklist.h +++ b/src/include/storage/lwlocklist.h @@ -85,6 +85,7 @@ PG_LWLOCK(50, DSMRegistry) PG_LWLOCK(51, InjectionPoint) PG_LWLOCK(52, SerialControl) PG_LWLOCK(53, AioWorkerSubmissionQueue) +PG_LWLOCK(54, WaitLSN) /* * There also exist several built-in LWLock tranches. As with the predefined -- 2.51.0