agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH] Fix a few problems in index build progress reporting. 55+ messages / 2 participants [nested] [flat]
* [PATCH] Fix a few problems in index build progress reporting. @ 2026-03-16 12:53 Antonin Houska <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Antonin Houska @ 2026-03-16 12:53 UTC (permalink / raw) First, index_build() should not update the progress when being driven by REPACK, because the progress reporting infractructure cannot handle status of two commands at the same time. So far, REPACK with the CONCURRENTLY option neglected this problem altogether, but even the existing REPACK wasn't consistent enough: even if the 'progress' variable in repack_index() was false, it didn't pass the value to index_build(). Second, REPACK (CONCURRENTLY) should not set PROGRESS_REPACK_PHASE to PROGRESS_REPACK_PHASE_FINAL_CLEANUP in rebuild_relation() because it calls finish_heap_swap() anyway (via rebuild_relation_finish_concurrent()), which does the same thing. --- src/backend/bootstrap/bootstrap.c | 2 +- src/backend/catalog/heap.c | 3 ++- src/backend/catalog/index.c | 22 ++++++++++++++++++---- src/backend/catalog/toasting.c | 3 ++- src/backend/commands/cluster.c | 7 ++++--- src/backend/commands/indexcmds.c | 1 + src/include/catalog/index.h | 4 +++- 7 files changed, 31 insertions(+), 11 deletions(-) diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c index 17118f2fe76..cb06c52c1d4 100644 --- a/src/backend/bootstrap/bootstrap.c +++ b/src/backend/bootstrap/bootstrap.c @@ -1180,7 +1180,7 @@ build_indices(void) heap = table_open(ILHead->il_heap, NoLock); ind = index_open(ILHead->il_ind, NoLock); - index_build(heap, ind, ILHead->il_info, false, false); + index_build(heap, ind, ILHead->il_info, false, false, false); index_close(ind, NoLock); table_close(heap, NoLock); diff --git a/src/backend/catalog/heap.c b/src/backend/catalog/heap.c index 5748aa9a1a9..ae6b7cda3dd 100644 --- a/src/backend/catalog/heap.c +++ b/src/backend/catalog/heap.c @@ -3570,7 +3570,8 @@ RelationTruncateIndexes(Relation heapRelation) /* Initialize the index and rebuild */ /* Note: we do not need to re-establish pkey setting */ - index_build(heapRelation, currentIndex, indexInfo, true, false); + index_build(heapRelation, currentIndex, indexInfo, true, false, + true); /* We're done with this index */ index_close(currentIndex, NoLock); diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c index b1e05d56a1e..89aad2f7b77 100644 --- a/src/backend/catalog/index.c +++ b/src/backend/catalog/index.c @@ -714,6 +714,9 @@ UpdateIndexRelation(Oid indexoid, * already exists. * INDEX_CREATE_PARTITIONED: * create a partitioned index (table must be partitioned) + * INDEX_CREATE_REPORT_PROGRESS: + * update the backend's progress information during index build. + * constr_flags: flags passed to index_constraint_create * (only if INDEX_CREATE_ADD_CONSTRAINT is set) * allow_system_table_mods: allow table to be a system catalog @@ -759,6 +762,7 @@ index_create(Relation heapRelation, bool invalid = (flags & INDEX_CREATE_INVALID) != 0; bool concurrent = (flags & INDEX_CREATE_CONCURRENT) != 0; bool partitioned = (flags & INDEX_CREATE_PARTITIONED) != 0; + bool progress = (flags & INDEX_CREATE_REPORT_PROGRESS) != 0; char relkind; TransactionId relfrozenxid; MultiXactId relminmxid; @@ -1275,7 +1279,8 @@ index_create(Relation heapRelation, } else { - index_build(heapRelation, indexRelation, indexInfo, false, true); + index_build(heapRelation, indexRelation, indexInfo, false, true, + progress); } /* @@ -1454,6 +1459,12 @@ index_create_copy(Relation heapRelation, Oid oldIndexId, Oid tablespaceOid, stattargets[i].isnull = isnull; } + /* + * Note: The current callers do not need INDEX_CREATE_REPORT_PROGRESS. If + * 'concurrently' is true, there is no build at all. Otherwise the index + * build is a sub-command of REPACK. The current infrastructure does not + * allow two commands to report their progress at the same time. + */ if (concurrently) flags = INDEX_CREATE_SKIP_BUILD | INDEX_CREATE_CONCURRENT; @@ -1544,7 +1555,7 @@ index_concurrently_build(Oid heapRelationId, indexInfo->ii_BrokenHotChain = false; /* Now build the index */ - index_build(heapRel, indexRelation, indexInfo, false, true); + index_build(heapRel, indexRelation, indexInfo, false, true, true); /* Roll back any GUC changes executed by index functions */ AtEOXact_GUC(false, save_nestlevel); @@ -3017,6 +3028,7 @@ index_update_stats(Relation rel, * * isreindex indicates we are recreating a previously-existing index. * parallel indicates if parallelism may be useful. + * progress indicates if the backend should update its progress info. * * Note: before Postgres 8.2, the passed-in heap and index Relations * were automatically closed by this routine. This is no longer the case. @@ -3027,7 +3039,8 @@ index_build(Relation heapRelation, Relation indexRelation, IndexInfo *indexInfo, bool isreindex, - bool parallel) + bool parallel, + bool progress) { IndexBuildResult *stats; Oid save_userid; @@ -3078,6 +3091,7 @@ index_build(Relation heapRelation, RestrictSearchPath(); /* Set up initial progress report status */ + if (progress) { const int progress_index[] = { PROGRESS_CREATEIDX_PHASE, @@ -3835,7 +3849,7 @@ reindex_index(const ReindexStmt *stmt, Oid indexId, /* Initialize the index and rebuild */ /* Note: we do not need to re-establish pkey setting */ - index_build(heapRelation, iRel, indexInfo, true, true); + index_build(heapRelation, iRel, indexInfo, true, true, progress); /* Re-allow use of target index */ ResetReindexProcessing(); diff --git a/src/backend/catalog/toasting.c b/src/backend/catalog/toasting.c index 078a1cf5127..73c41360ae9 100644 --- a/src/backend/catalog/toasting.c +++ b/src/backend/catalog/toasting.c @@ -331,7 +331,8 @@ create_toast_table(Relation rel, Oid toastOid, Oid toastIndexOid, BTREE_AM_OID, rel->rd_rel->reltablespace, collationIds, opclassIds, NULL, coloptions, NULL, (Datum) 0, - INDEX_CREATE_IS_PRIMARY, 0, true, true, NULL); + INDEX_CREATE_IS_PRIMARY | INDEX_CREATE_REPORT_PROGRESS, 0, + true, true, NULL); table_close(toast_rel, NoLock); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..9aaa8e95389 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1162,9 +1162,6 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, rebuild_relation_finish_concurrent(NewHeap, OldHeap, ident_idx, frozenXid, cutoffMulti); - - pgstat_progress_update_param(PROGRESS_REPACK_PHASE, - PROGRESS_REPACK_PHASE_FINAL_CLEANUP); } else { @@ -3505,6 +3502,10 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, relpersistence = OldHeap->rd_rel->relpersistence; is_system_catalog = IsSystemRelation(OldHeap); + /* + * finish_heap_swap() sets the phase too, but here we need some swapping + * in advance. + */ pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_SWAP_REL_FILES); diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c index 34209bd1393..ad5c1238e09 100644 --- a/src/backend/commands/indexcmds.c +++ b/src/backend/commands/indexcmds.c @@ -1230,6 +1230,7 @@ DefineIndex(ParseState *pstate, flags |= INDEX_CREATE_PARTITIONED; if (stmt->primary) flags |= INDEX_CREATE_IS_PRIMARY; + flags |= INDEX_CREATE_REPORT_PROGRESS; /* * If the table is partitioned, and recursion was declined but partitions diff --git a/src/include/catalog/index.h b/src/include/catalog/index.h index 3426087b445..3778e9b7f07 100644 --- a/src/include/catalog/index.h +++ b/src/include/catalog/index.h @@ -65,6 +65,7 @@ extern void index_check_primary_key(Relation heapRel, #define INDEX_CREATE_IF_NOT_EXISTS (1 << 4) #define INDEX_CREATE_PARTITIONED (1 << 5) #define INDEX_CREATE_INVALID (1 << 6) +#define INDEX_CREATE_REPORT_PROGRESS (1 << 7) extern Oid index_create(Relation heapRelation, const char *indexRelationName, @@ -146,7 +147,8 @@ extern void index_build(Relation heapRelation, Relation indexRelation, IndexInfo *indexInfo, bool isreindex, - bool parallel); + bool parallel, + bool progress); extern void validate_index(Oid heapId, Oid indexId, Snapshot snapshot); -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
* [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic @ 2026-07-09 19:20 Nathan Bossart <[email protected]> 0 siblings, 0 replies; 55+ messages in thread From: Nathan Bossart @ 2026-07-09 19:20 UTC (permalink / raw) --- src/backend/storage/ipc/sinvaladt.c | 51 ++++++++++------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/src/backend/storage/ipc/sinvaladt.c b/src/backend/storage/ipc/sinvaladt.c index 37a21ffaf1a..17e98c9efdc 100644 --- a/src/backend/storage/ipc/sinvaladt.c +++ b/src/backend/storage/ipc/sinvaladt.c @@ -24,7 +24,6 @@ #include "storage/procsignal.h" #include "storage/shmem.h" #include "storage/sinvaladt.h" -#include "storage/spin.h" #include "storage/subsystems.h" /* @@ -87,19 +86,10 @@ * has no need to touch anyone's ProcState, except in the infrequent cases * when SICleanupQueue is needed. The only point of overlap is that * the writer wants to change maxMsgNum while readers need to read it. - * We deal with that by having a spinlock that readers must take for just - * long enough to read maxMsgNum, while writers take it for just long enough - * to write maxMsgNum. (The exact rule is that you need the spinlock to - * read maxMsgNum if you are not holding SInvalWriteLock, and you need the - * spinlock to write maxMsgNum unless you are holding both locks.) - * - * Note: since maxMsgNum is an int and hence presumably atomically readable/ - * writable, the spinlock might seem unnecessary. The reason it is needed - * is to provide a memory barrier: we need to be sure that messages written - * to the array are actually there before maxMsgNum is increased, and that - * readers will see that data after fetching maxMsgNum. Multiprocessors - * that have weak memory-ordering guarantees can fail without the memory - * barrier instructions that are included in the spinlock sequences. + * We deal with that by making maxMsgNum an atomic variable. (The exact rule + * is that you need to use a barrier-providing accessor to read maxMsgNum if + * you are not holding SInvalWriteLock, and you need a barrier-providing + * accessor to write maxMsgNum unless you are holding both locks.) */ @@ -169,11 +159,9 @@ typedef struct SISeg * General state information */ int minMsgNum; /* oldest message still needed */ - int maxMsgNum; /* next message number to be assigned */ + pg_atomic_uint32 maxMsgNum; /* next message number to be assigned */ int nextThreshold; /* # of messages to call SICleanupQueue */ - slock_t msgnumLock; /* spinlock protecting maxMsgNum */ - /* * Circular buffer holding shared-inval messages */ @@ -244,11 +232,10 @@ SharedInvalShmemInit(void *arg) { int i; - /* Clear message counters, init spinlock */ + /* Clear message counters */ shmInvalBuffer->minMsgNum = 0; - shmInvalBuffer->maxMsgNum = 0; + pg_atomic_init_u32(&shmInvalBuffer->maxMsgNum, 0); shmInvalBuffer->nextThreshold = CLEANUP_MIN; - SpinLockInit(&shmInvalBuffer->msgnumLock); /* The buffer[] array is initially all unused, so we need not fill it */ @@ -306,7 +293,7 @@ SharedInvalBackendInit(bool sendOnly) /* mark myself active, with all extant messages already read */ stateP->procPid = MyProcPid; - stateP->nextMsgNum = segP->maxMsgNum; + stateP->nextMsgNum = pg_atomic_read_u32(&segP->maxMsgNum); stateP->resetState = false; stateP->signaled = false; stateP->hasMessages = false; @@ -402,7 +389,7 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) */ for (;;) { - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs + nthistime > MAXNUMMESSAGES || numMsgs >= segP->nextThreshold) SICleanupQueue(true, nthistime); @@ -413,17 +400,15 @@ SIInsertDataEntries(const SharedInvalidationMessage *data, int n) /* * Insert new message(s) into proper slot of circular buffer */ - max = segP->maxMsgNum; + max = pg_atomic_read_u32(&segP->maxMsgNum); while (nthistime-- > 0) { segP->buffer[max % MAXNUMMESSAGES] = *data++; max++; } - /* Update current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - segP->maxMsgNum = max; - SpinLockRelease(&segP->msgnumLock); + /* Update current value of maxMsgNum using barrier */ + pg_atomic_write_membarrier_u32(&segP->maxMsgNum, max); /* * Now that the maxMsgNum change is globally visible, we give everyone @@ -509,10 +494,8 @@ SIGetDataEntries(SharedInvalidationMessage *data, int datasize) */ stateP->hasMessages = false; - /* Fetch current value of maxMsgNum using spinlock */ - SpinLockAcquire(&segP->msgnumLock); - max = segP->maxMsgNum; - SpinLockRelease(&segP->msgnumLock); + /* Fetch current value of maxMsgNum using barrier */ + max = pg_atomic_read_membarrier_u32(&segP->maxMsgNum); if (stateP->resetState) { @@ -598,7 +581,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * backends here it is possible for them to keep sending messages without * a problem even when they are the only active backend. */ - min = segP->maxMsgNum; + min = pg_atomic_read_u32(&segP->maxMsgNum); minsig = min - SIG_THRESHOLD; lowbound = min - MAXNUMMESSAGES + minFree; @@ -644,7 +627,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) if (min >= MSGNUMWRAPAROUND) { segP->minMsgNum -= MSGNUMWRAPAROUND; - segP->maxMsgNum -= MSGNUMWRAPAROUND; + pg_atomic_fetch_sub_u32(&segP->maxMsgNum, MSGNUMWRAPAROUND); for (i = 0; i < segP->numProcs; i++) segP->procState[segP->pgprocnos[i]].nextMsgNum -= MSGNUMWRAPAROUND; } @@ -653,7 +636,7 @@ SICleanupQueue(bool callerHasWriteLock, int minFree) * Determine how many messages are still in the queue, and set the * threshold at which we should repeat SICleanupQueue(). */ - numMsgs = segP->maxMsgNum - segP->minMsgNum; + numMsgs = pg_atomic_read_u32(&segP->maxMsgNum) - segP->minMsgNum; if (numMsgs < CLEANUP_MIN) segP->nextThreshold = CLEANUP_MIN; else -- 2.50.1 (Apple Git-155) --Ot5x3ffkWEuxilWO Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename=v1-0002-convert-ParallelBitmapHeapState-state-to-an-atomi.patch ^ permalink raw reply [nested|flat] 55+ messages in thread
end of thread, other threads:[~2026-07-09 19:20 UTC | newest] Thread overview: 55+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2026-03-16 12:53 [PATCH] Fix a few problems in index build progress reporting. Antonin Houska <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]> 2026-07-09 19:20 [PATCH v1 1/8] convert SISeg->maxMsgNum to an atomic Nathan Bossart <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox