From a62922a732b261ccfe5c7623aa4fe0e9b18c4aeb Mon Sep 17 00:00:00 2001 From: Maksim Melnikov Date: Tue, 18 Nov 2025 17:20:09 +0300 Subject: [PATCH v5] This patch reduce connection init/close time. ProcArrayRemove/ProcArrayAdd are expensive in terms of accessing pgxactoff field in PGPROC, because its are placed on different pages and it the reason of page_faults occurence. Now one of the use case with pgxactoff is iteration with gaps over PGPROCs and read/write pgxactoff, PGPROC allocate ~1KB and it quite enough to have page_faults in case of such accessing. So we placed all pgxactoff in the separate array pgxactoffs to have adjacent pages for them all. Indexes in allProcs aligned with pgxactoffs array, so the Nth element in pgxactoffs refer to Nth PGPROC. Eventually it helps to avoid extra page_faults and reduce connection init/close time. The main benefit is seen on configurations without huge pages. --- src/backend/access/transam/varsup.c | 10 ++--- src/backend/commands/indexcmds.c | 2 +- src/backend/commands/vacuum.c | 2 +- src/backend/replication/logical/logical.c | 2 +- src/backend/replication/slot.c | 2 +- src/backend/replication/walsender.c | 2 +- src/backend/storage/ipc/procarray.c | 55 ++++++++++++++--------- src/backend/storage/lmgr/proc.c | 6 ++- src/include/storage/proc.h | 23 ++++++---- 9 files changed, 63 insertions(+), 41 deletions(-) diff --git a/src/backend/access/transam/varsup.c b/src/backend/access/transam/varsup.c index cb68d8fa974..d67c00b35c8 100644 --- a/src/backend/access/transam/varsup.c +++ b/src/backend/access/transam/varsup.c @@ -85,7 +85,7 @@ GetNewTransactionId(bool isSubXact) { Assert(!isSubXact); MyProc->xid = BootstrapTransactionId; - ProcGlobal->xids[MyProc->pgxactoff] = BootstrapTransactionId; + ProcGlobal->xids[ProcGetMyXactOff()] = BootstrapTransactionId; return FullTransactionIdFromEpochAndXid(0, BootstrapTransactionId); } @@ -244,18 +244,18 @@ GetNewTransactionId(bool isSubXact) */ if (!isSubXact) { - Assert(ProcGlobal->subxidStates[MyProc->pgxactoff].count == 0); - Assert(!ProcGlobal->subxidStates[MyProc->pgxactoff].overflowed); + Assert(ProcGlobal->subxidStates[ProcGetMyXactOff()].count == 0); + Assert(!ProcGlobal->subxidStates[ProcGetMyXactOff()].overflowed); Assert(MyProc->subxidStatus.count == 0); Assert(!MyProc->subxidStatus.overflowed); /* LWLockRelease acts as barrier */ MyProc->xid = xid; - ProcGlobal->xids[MyProc->pgxactoff] = xid; + ProcGlobal->xids[ProcGetMyXactOff()] = xid; } else { - XidCacheStatus *substat = &ProcGlobal->subxidStates[MyProc->pgxactoff]; + XidCacheStatus *substat = &ProcGlobal->subxidStates[ProcGetMyXactOff()]; int nxids = MyProc->subxidStatus.count; Assert(substat->count == MyProc->subxidStatus.count); diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c index 5a0312fe772..4c66e7bb917 100644 --- a/src/backend/commands/indexcmds.c +++ b/src/backend/commands/indexcmds.c @@ -4811,6 +4811,6 @@ set_indexsafe_procflags(void) LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); MyProc->statusFlags |= PROC_IN_SAFE_IC; - ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + ProcGlobal->statusFlags[ProcGetMyXactOff()] = MyProc->statusFlags; LWLockRelease(ProcArrayLock); } diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c index 72c7f680a84..a2b853e85a4 100644 --- a/src/backend/commands/vacuum.c +++ b/src/backend/commands/vacuum.c @@ -2081,7 +2081,7 @@ vacuum_rel(Oid relid, RangeVar *relation, VacuumParams params, MyProc->statusFlags |= PROC_IN_VACUUM; if (params.is_wraparound) MyProc->statusFlags |= PROC_VACUUM_FOR_WRAPAROUND; - ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + ProcGlobal->statusFlags[ProcGetMyXactOff()] = MyProc->statusFlags; LWLockRelease(ProcArrayLock); } diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index 98e5f1dd8f9..53c521f129f 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -274,7 +274,7 @@ StartupDecodingContext(List *output_plugin_options, { LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); MyProc->statusFlags |= PROC_IN_LOGICAL_DECODING; - ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + ProcGlobal->statusFlags[ProcGetMyXactOff()] = MyProc->statusFlags; LWLockRelease(ProcArrayLock); } diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 63ce6d27885..9c2a2cb9888 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -834,7 +834,7 @@ ReplicationSlotRelease(void) /* might not have been set when we've been a plain slot */ LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); MyProc->statusFlags &= ~PROC_IN_LOGICAL_DECODING; - ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + ProcGlobal->statusFlags[ProcGetMyXactOff()] = MyProc->statusFlags; LWLockRelease(ProcArrayLock); if (am_walsender) diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c index c65dd324325..98217943dfa 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -358,7 +358,7 @@ InitWalSender(void) Assert(MyProc->xmin == InvalidTransactionId); LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); MyProc->statusFlags |= PROC_AFFECTS_ALL_HORIZONS; - ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + ProcGlobal->statusFlags[ProcGetMyXactOff()] = MyProc->statusFlags; LWLockRelease(ProcArrayLock); } diff --git a/src/backend/storage/ipc/procarray.c b/src/backend/storage/ipc/procarray.c index b7e03134ed8..090338fb63b 100644 --- a/src/backend/storage/ipc/procarray.c +++ b/src/backend/storage/ipc/procarray.c @@ -284,6 +284,13 @@ typedef enum KAXCompressReason static PGPROC *allProcs; +/* + * offsets into various ProcGlobal->arrays with data mirrored from + * appropriate PGPROCs, procno define offset index in pgxactoffs array(See + * PROC_HDR for details). + */ +static int *pgxactoffs; + /* * Cache to reduce overhead of repeated calls to TransactionIdIsInProgress() */ @@ -449,12 +456,14 @@ ProcArrayShmemInit(void *arg) TransamVariables->xactCompletionCount = 1; allProcs = ProcGlobal->allProcs; + pgxactoffs = ProcGlobal->pgxactoffs; } static void ProcArrayShmemAttach(void *arg) { allProcs = ProcGlobal->allProcs; + pgxactoffs = ProcGlobal->pgxactoffs; } /* @@ -498,7 +507,7 @@ ProcArrayAdd(PGPROC *proc) int this_procno = arrayP->pgprocnos[index]; Assert(this_procno >= 0 && this_procno < (arrayP->maxProcs + NUM_AUXILIARY_PROCS)); - Assert(allProcs[this_procno].pgxactoff == index); + Assert(pgxactoffs[this_procno] == index); /* If we have found our right position in the array, break */ if (this_procno > pgprocno) @@ -520,23 +529,23 @@ ProcArrayAdd(PGPROC *proc) movecount * sizeof(*ProcGlobal->statusFlags)); arrayP->pgprocnos[index] = pgprocno; - proc->pgxactoff = index; + pgxactoffs[arrayP->pgprocnos[index]] = index; ProcGlobal->xids[index] = proc->xid; ProcGlobal->subxidStates[index] = proc->subxidStatus; ProcGlobal->statusFlags[index] = proc->statusFlags; arrayP->numProcs++; - /* adjust pgxactoff for all following PGPROCs */ + /* adjust appropriate pgxactoff for all following PGPROCs */ index++; for (; index < arrayP->numProcs; index++) { int procno = arrayP->pgprocnos[index]; Assert(procno >= 0 && procno < (arrayP->maxProcs + NUM_AUXILIARY_PROCS)); - Assert(allProcs[procno].pgxactoff == index - 1); + Assert(pgxactoffs[procno] == index - 1); - allProcs[procno].pgxactoff = index; + pgxactoffs[procno] = index; } /* @@ -574,10 +583,10 @@ ProcArrayRemove(PGPROC *proc, TransactionId latestXid) LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); LWLockAcquire(XidGenLock, LW_EXCLUSIVE); - myoff = proc->pgxactoff; + myoff = ProcGetXactOff(GetNumberFromPGProc(proc)); Assert(myoff >= 0 && myoff < arrayP->numProcs); - Assert(ProcGlobal->allProcs[arrayP->pgprocnos[myoff]].pgxactoff == myoff); + Assert(ProcGlobal->pgxactoffs[arrayP->pgprocnos[myoff]] == myoff); if (TransactionIdIsValid(latestXid)) { @@ -624,17 +633,17 @@ ProcArrayRemove(PGPROC *proc, TransactionId latestXid) arrayP->numProcs--; /* - * Adjust pgxactoff of following procs for removed PGPROC (note that - * numProcs already has been decremented). + * Adjust appropriate pgxactoff of following procs for removed PGPROC + * (note that numProcs already has been decremented). */ for (int index = myoff; index < arrayP->numProcs; index++) { int procno = arrayP->pgprocnos[index]; Assert(procno >= 0 && procno < (arrayP->maxProcs + NUM_AUXILIARY_PROCS)); - Assert(allProcs[procno].pgxactoff - 1 == index); + Assert(pgxactoffs[procno] - 1 == index); - allProcs[procno].pgxactoff = index; + pgxactoffs[procno] = index; } /* @@ -706,11 +715,13 @@ ProcArrayEndTransaction(PGPROC *proc, TransactionId latestXid) /* avoid unnecessarily dirtying shared cachelines */ if (proc->statusFlags & PROC_VACUUM_STATE_MASK) { + int pgxactoff = ProcGetXactOff(GetNumberFromPGProc(proc)); + Assert(!LWLockHeldByMe(ProcArrayLock)); LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); - Assert(proc->statusFlags == ProcGlobal->statusFlags[proc->pgxactoff]); + Assert(proc->statusFlags == ProcGlobal->statusFlags[pgxactoff]); proc->statusFlags &= ~PROC_VACUUM_STATE_MASK; - ProcGlobal->statusFlags[proc->pgxactoff] = proc->statusFlags; + ProcGlobal->statusFlags[pgxactoff] = proc->statusFlags; LWLockRelease(ProcArrayLock); } } @@ -724,7 +735,7 @@ ProcArrayEndTransaction(PGPROC *proc, TransactionId latestXid) static inline void ProcArrayEndTransactionInternal(PGPROC *proc, TransactionId latestXid) { - int pgxactoff = proc->pgxactoff; + int pgxactoff = ProcGetXactOff(GetNumberFromPGProc(proc)); /* * Note: we need exclusive lock here because we're going to change other @@ -747,7 +758,7 @@ ProcArrayEndTransactionInternal(PGPROC *proc, TransactionId latestXid) if (proc->statusFlags & PROC_VACUUM_STATE_MASK) { proc->statusFlags &= ~PROC_VACUUM_STATE_MASK; - ProcGlobal->statusFlags[proc->pgxactoff] = proc->statusFlags; + ProcGlobal->statusFlags[pgxactoff] = proc->statusFlags; } /* Clear the subtransaction-XID cache too while holding the lock */ @@ -903,7 +914,7 @@ ProcArrayClearTransaction(PGPROC *proc) /* * Currently we need to lock ProcArrayLock exclusively here, as we * increment xactCompletionCount below. We also need it at least in shared - * mode for pgproc->pgxactoff to stay the same below. + * mode for proc's pgxactoff to stay the same below. * * We could however, as this action does not actually change anyone's view * of the set of running XIDs (our entry is duplicate with the gxact that @@ -916,7 +927,7 @@ ProcArrayClearTransaction(PGPROC *proc) */ LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); - pgxactoff = proc->pgxactoff; + pgxactoff = ProcGetXactOff(GetNumberFromPGProc(proc)); ProcGlobal->xids[pgxactoff] = InvalidTransactionId; proc->xid = InvalidTransactionId; @@ -1475,7 +1486,7 @@ TransactionIdIsInProgress(TransactionId xid) } /* No shortcuts, gotta grovel through the array */ - mypgxactoff = MyProc->pgxactoff; + mypgxactoff = ProcGetMyXactOff(); numProcs = arrayP->numProcs; for (int pgxactoff = 0; pgxactoff < numProcs; pgxactoff++) { @@ -2184,7 +2195,7 @@ GetSnapshotData(Snapshot snapshot) } latest_completed = TransamVariables->latestCompletedXid; - mypgxactoff = MyProc->pgxactoff; + mypgxactoff = ProcGetMyXactOff(); myxid = other_xids[mypgxactoff]; Assert(myxid == MyProc->xid); @@ -2223,7 +2234,7 @@ GetSnapshotData(Snapshot snapshot) TransactionId xid = UINT32_ACCESS_ONCE(other_xids[pgxactoff]); uint8 statusFlags; - Assert(allProcs[arrayP->pgprocnos[pgxactoff]].pgxactoff == pgxactoff); + Assert(pgxactoffs[arrayP->pgprocnos[pgxactoff]] == pgxactoff); /* * If the transaction has no XID assigned, we can skip it; it @@ -2596,7 +2607,7 @@ ProcArrayInstallRestoredXmin(TransactionId xmin, PGPROC *proc) MyProc->xmin = TransactionXmin = xmin; MyProc->statusFlags = (MyProc->statusFlags & ~PROC_XMIN_FLAGS) | (proc->statusFlags & PROC_XMIN_FLAGS); - ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + ProcGlobal->statusFlags[ProcGetMyXactOff()] = MyProc->statusFlags; result = true; } @@ -4024,7 +4035,7 @@ XidCacheRemoveRunningXids(TransactionId xid, */ LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); - mysubxidstat = &ProcGlobal->subxidStates[MyProc->pgxactoff]; + mysubxidstat = &ProcGlobal->subxidStates[ProcGetMyXactOff()]; /* * Under normal circumstances xid and xids[] will be in increasing order, diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 624cecc6bc5..053538ccebd 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -163,6 +163,7 @@ ProcGlobalShmemRequest(void *arg) size = add_size(size, mul_size(TotalProcs, sizeof(PGPROC))); size = add_size(size, mul_size(TotalProcs, sizeof(*ProcGlobal->xids))); size = add_size(size, mul_size(TotalProcs, sizeof(*ProcGlobal->subxidStates))); + size = add_size(size, mul_size(TotalProcs, sizeof(*ProcGlobal->pgxactoffs))); size = add_size(size, mul_size(TotalProcs, sizeof(*ProcGlobal->statusFlags))); ProcGlobalAllProcsShmemSize = size; ShmemRequestStruct(.name = "PGPROC structures", @@ -267,6 +268,9 @@ ProcGlobalShmemInit(void *arg) ProcGlobal->xids = (TransactionId *) ptr; ptr = ptr + (TotalProcs * sizeof(*ProcGlobal->xids)); + ProcGlobal->pgxactoffs = (int *) ptr; + ptr = ptr + (TotalProcs * sizeof(*ProcGlobal->pgxactoffs)); + ProcGlobal->subxidStates = (XidCacheStatus *) ptr; ptr = ptr + (TotalProcs * sizeof(*ProcGlobal->subxidStates)); @@ -1555,7 +1559,7 @@ ProcSleep(LOCALLOCK *locallock) * the lock held, which is much more undesirable. */ LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); - statusFlags = ProcGlobal->statusFlags[autovac->pgxactoff]; + statusFlags = ProcGlobal->statusFlags[ProcGetXactOff(GetNumberFromPGProc(autovac))]; lockmethod_copy = lock->tag.locktag_lockmethodid; locktag_copy = lock->tag; LWLockRelease(ProcArrayLock); diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 03a1a466fa8..8cbc8928dd5 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -174,7 +174,8 @@ typedef enum * * Some fields in PGPROC (see "mirrored in ..." comment) are mirrored into an * element of more densely packed ProcGlobal arrays. These arrays are indexed - * by PGPROC->pgxactoff. Both copies need to be maintained coherently. + * by a PGPROC's pgxactoffs entry. Both copies need to be maintained + * coherently. * * NB: The pgxactoff indexed value can *never* be accessed without holding * locks. @@ -210,9 +211,6 @@ typedef struct PGPROC Oid tempNamespaceId; /* OID of temp schema this backend is * using */ - int pgxactoff; /* offset into various ProcGlobal->arrays with - * data mirrored from this PGPROC */ - uint8 statusFlags; /* this backend's status flags, see PROC_* * above. mirrored in * ProcGlobal->statusFlags[pgxactoff] */ @@ -402,10 +400,11 @@ extern PGDLLIMPORT PGPROC *MyProc; * for PGPROCs that have been added to the shared array with ProcArrayAdd() * (in contrast to PGPROC array which has unused PGPROCs interspersed). * - * The dense arrays are indexed by PGPROC->pgxactoff. Any concurrent - * ProcArrayAdd() / ProcArrayRemove() can lead to pgxactoff of a procarray - * member to change. Therefore it is only safe to use PGPROC->pgxactoff to - * access the dense array while holding either ProcArrayLock or XidGenLock. + * The dense arrays are indexed by the PGPROC's corresponding offset in + * pgxactoff. Any concurrent ProcArrayAdd() / ProcArrayRemove() can cause + * the pgxactoff of a procarray member to change. Therefore it is only safe + * to use a proc's pgxactoff to access the dense array while holding either + * ProcArrayLock or XidGenLock. * * As long as a PGPROC is in the procarray, the mirrored values need to be * maintained in both places in a coherent manner. @@ -446,6 +445,12 @@ typedef struct PROC_HDR /* Array of PGPROC structures (not including dummies for prepared txns) */ PGPROC *allProcs; + /* + * Dense offsets into various ProcGlobal->arrays with data mirrored from + * appropriate PGPROCs. Like allProcs, values are indexed by ProcNumber. + */ + int *pgxactoffs; + /* Array mirroring PGPROC.xid for each PGPROC currently in the procarray */ TransactionId *xids; @@ -511,6 +516,8 @@ extern PGDLLIMPORT PGPROC *PreparedXactProcs; */ #define GetPGProcByNumber(n) (&ProcGlobal->allProcs[(n)]) #define GetNumberFromPGProc(proc) ((proc) - &ProcGlobal->allProcs[0]) +#define ProcGetXactOff(procno) (ProcGlobal->pgxactoffs[(procno)]) +#define ProcGetMyXactOff() (ProcGetXactOff(MyProcNumber)) /* * We set aside some extra PGPROC structures for "special worker" processes, -- 2.43.0